We introduce a two-dimensional (2D) early exit strategy that coordinates layer-wise and sentence-wise exiting for classification tasks in large language models. By processing input incrementally sentence-by-sentence while progressively activating deeper layers, our method achieves multiplicative computational savings that exceed those from optimizing either dimension independently. Experimental evaluation across four state-of-the-art LLMs (Llama 3.1, Llama 3.2, Gemma, Qwen; 3B-8B parameters) on three sentiment classification datasets demonstrates additional speed-ups of 1.4--2.3$\times$ over optimal layer-wise early exit for simpler tasks with vanilla models, with graceful degradation on complex multi-class problems. Fine-tuning reduces but does not eliminate this advantage. The approach is model-agnostic, requires only lightweight classification adapters, and is orthogonal to complementary efficiency methods such as quantization and pruning. Our findings indicate that 2D early exit strategies excel when semantic information accumulates predictably across input structure, suggesting possible applicability to sequence-processing tasks beyond sentiment classification.
https://arxiv.org/abs/2604.18592
Determining whether a piece of text is relevant to a given topic is a fundamental task in natural language processing, yet it remains largely unexplored for Bahasa Indonesia. Unlike sentiment analysis or named entity recognition, relevancy classification requires the model to reason about the relationship between two inputs simultaneously: a topical context and a candidate text. We introduce IndoBERT-Relevancy, a context-conditioned relevancy classifier built on IndoBERT Large (335M parameters) and trained on a novel dataset of 31,360 labeled pairs spanning 188 topics. Through an iterative, failure-driven data construction process, we demonstrate that no single data source is sufficient for robust relevancy classification, and that targeted synthetic data can effectively address specific model weaknesses. Our final model achieves an F1 score of 0.948 and an accuracy of 96.5%, handling both formal and informal Indonesian text. The model is publicly available at HuggingFace.
https://arxiv.org/abs/2603.26095
This study presents a computational analysis of the Slovene historical newspapers \textit{Slovenec} and \textit{Slovenski narod} from the sPeriodika corpus, combining topic modelling, large language model (LLM)-based aspect-level sentiment analysis, entity-graph visualisation, and qualitative discourse analysis to examine how collective identities, political orientations, and national belonging were represented in public discourse at the turn of the twentieth century. Using BERTopic, we identify major thematic patterns and show both shared concerns and clear ideological differences between the two newspapers, reflecting their conservative-Catholic and liberal-progressive orientations. We further evaluate four instruction-following LLMs for targeted sentiment classification in OCR-degraded historical Slovene and select the Slovene-adapted GaMS3-12B-Instruct model as the most suitable for large-scale application, while also documenting important limitations, particularly its stronger performance on neutral sentiment than on positive or negative sentiment. Applied at dataset scale, the model reveals meaningful variation in the portrayal of collective identities, with some groups appearing predominantly in neutral descriptive contexts and others more often in evaluative or conflict-related discourse. We then create NER graphs to explore the relationships between collective identities and places. We apply a mixed methods approach to analyse the named entity graphs, combining quantitative network analysis with critical discourse analysis. The investigation focuses on the emergence and development of intertwined historical political and socionomic identities. Overall, the study demonstrates the value of combining scalable computational methods with critical interpretation to support digital humanities research on noisy historical newspaper data.
本研究对sPeriodika语料库中的斯洛文尼亚历史报纸《Slovenec》与《Slovenski narod》进行了计算分析,综合运用主题建模、基于大语言模型(LLM)的方面级情感分析、实体图可视化及质性话语分析,探究20世纪之交公共话语中集体身份、政治倾向与国家归属的呈现方式。通过BERTopic识别主要主题模式,揭示两份报纸在保守-天主教与自由-进步取向下的共同关切与明显意识形态差异。研究还评估了四种指令遵循型大语言模型对光学字符识别(OCR)受损的历史斯洛文尼亚语文本进行定向情感分类的效果,选定经斯洛文尼亚语优化的GaMS3-12B-Instruct模型作为大规模应用的最佳选择,同时记录其重要局限——该模型在中性情感识别上表现显著优于积极或消极情感。在数据集层面应用该模型发现,集体身份的 portrayal 存在显著差异:部分群体主要出现在中性描述语境中,而另一些则更频繁出现在评价性或冲突相关话语里。随后构建命名实体图以探索集体身份与地点的关联,采用混合方法分析实体图,结合量化网络分析与批判性话语分析,聚焦历史政治与社会经济身份的交织演进。整体而言,本研究展示了将可扩展计算方法与批判性阐释相结合的价值,为处理噪声较大的历史报纸数据的数字人文研究提供了支持。
https://arxiv.org/abs/2603.25051
This paper describes LogSigma, our system for SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA). Unlike traditional Aspect-Based Sentiment Analysis (ABSA), which predicts discrete sentiment labels, DimABSA requires predicting continuous Valence and Arousal (VA) scores on a 1-9 scale. A central challenge is that Valence and Arousal differ in prediction difficulty across languages and domains. We address this using learned homoscedastic uncertainty, where the model learns task-specific log-variance parameters to automatically balance each regression objective during training. Combined with language-specific encoders and multi-seed ensembling, LogSigma achieves 1st place on five datasets across both tracks. The learned variance weights vary substantially across languages due to differing Valence-Arousal difficulty profiles-from 0.66x for German to 2.18x for English-demonstrating that optimal task balancing is language-dependent and cannot be determined a priori.
本文介绍LogSigma,我们为SemEval-2026任务3:维度化方面情感分析(DimABSA)所开发的系统。与传统方面情感分析(ABSA)预测离散情感标签不同,DimABSA要求预测1-9量程上的连续效价(Valence)与唤醒度(Arousal)分数。核心挑战在于效价与唤醒度在不同语言与领域中的预测难度存在差异。我们通过采用学习同方差不确定性(learned homoscedastic uncertainty)方法解决此问题,即模型在学习过程中自动调整各回归目标的任务特定对数方差参数,以实现训练时的动态平衡。结合语言特定编码器与多种子集成策略,LogSigma在双轨共计五个数据集上均取得第一名。实验显示,由于不同语言的效价-唤醒度难度谱系各异,所学方差权重在语言间存在显著差异——德语为0.66倍,英语则为2.18倍——这表明最优任务平衡具有语言依赖性,无法预先确定。
https://arxiv.org/abs/2603.24896
Virtual influencers~(VIs) -- digitally synthetic social-media personas -- attract audiences whose discourse appears qualitatively different from discourse around human influencers~(HIs). Existing work characterises this difference through surveys or aggregate engagement statistics, which reveal \emph{what} audiences say but not \emph{how} multiple signals co-occur. We propose a two-layer, structure-first framework grounded in Formal Concept Analysis~(FCA) and association rule mining. The first layer applies FCA with support-based iceberg filtering to weekly-aggregated comment data, extracting discourse profiles -- weekly co-occurrence bundles of sentiment, Big Five personality cues, and topic tags. The second layer mines association rules at the comment level, revealing personality--sentiment--topic dependencies invisible to frequency-table analysis. Applied to YouTube comments from three VI--HI influencer pairs, the two-layer analysis reveals a consistent structural divergence: HI discourse concentrates into a single, emotionally regulated (stability-centred) regime (low neuroticism anchoring positivity), while VI discourse supports three structurally distinct discourse modes, including an appearance-discourse cluster absent from HI despite near-equal marginal prevalence. Topic-specific analyses further show that VI contexts exhibit negative sentiment in psychologically sensitive domains (mental health, body image, artificial identity) relative to HI contexts. Our results position FCA as a principled tool for multi-signal discourse analysis and demonstrate that virtuality reshapes not just what audiences say, but the underlying grammar of how signals co-occur in their reactions.
虚拟影响者(VIs)——数字合成的社交媒体人格——所吸引的受众,其话语在质上与围绕人类影响者(HIs)的话语存在差异。现有研究通过调查或聚合互动统计数据来刻画这种差异,这些数据揭示了受众“说什么”,却未揭示多重信号“如何”共现。我们提出一个基于形式概念分析(FCA)和关联规则挖掘的、以结构为先导的双层框架。第一层应用FCA并结合基于支持度的冰山过滤,处理按周聚合的评论数据,提取话语轮廓——即情感、大五人格线索与话题标签的周度共现组合。第二层在评论层面挖掘关联规则,揭示频率表分析无法发现的人格-情感-话题依赖关系。通过对三组VI-HI影响者配对的YouTube评论进行双层分析,发现一致的结构性差异:HI话语集中于单一、情感受控(以稳定性为中心)的形态(低神经质锚定积极性),而VI话语则支撑三种结构上不同的话语模式,其中包括一个在HI中缺失的“外貌话语”集群——尽管其边际出现率相近。话题特异性分析进一步显示,在心理敏感领域(心理健康、身体形象、人工身份),VI语境中的负面情感相较于HI语境更为显著。我们的研究将FCA定位为多信号话语分析的原则性工具,并证明虚拟性不仅重塑了受众“说什么”,更改变了其反应中信号共现的底层语法。
https://arxiv.org/abs/2603.24410
Environmental, Social, and Governance (ESG) principles are reshaping the foundations of global financial gover- nance, transforming capital allocation architectures, regu- latory frameworks, and systemic risk coordination mecha- nisms. However, as the core medium for assessing corpo- rate ESG performance, the ESG reports present significant challenges for large-scale understanding, due to chaotic read- ing order from slide-like irregular layouts and implicit hier- archies arising from lengthy, weakly structured content. To address these challenges, we propose Pharos-ESG, a uni- fied framework that transforms ESG reports into structured representations through multimodal parsing, contextual nar- ration, and hierarchical labeling. It integrates a reading-order modeling module based on layout flow, hierarchy-aware seg- mentation guided by table-of-contents anchors, and a multi- modal aggregation pipeline that contextually transforms vi- sual elements into coherent natural language. The framework further enriches its outputs with ESG, GRI, and sentiment labels, yielding annotations aligned with the analytical de- mands of financial research. Extensive experiments on anno- tated benchmarks demonstrate that Pharos-ESG consistently outperforms both dedicated document parsing systems and general-purpose multimodal models. In addition, we release Aurora-ESG, the first large-scale public dataset of ESG re- ports, spanning Mainland China, Hong Kong, and U.S. mar- kets, featuring unified structured representations of multi- modal content, enriched with fine-grained layout and seman- tic annotations to better support ESG integration in financial governance and decision-making.
环境、社会与治理(ESG)原则正在重塑全球金融治理的基础,改变资本配置架构、监管框架和系统性风险协调机制。然而,作为评估企业ESG表现的核心媒介,ESG报告因其类似幻灯片的非规整布局导致的阅读顺序混乱,以及内容冗长且结构松散而产生的隐性层级关系,给大规模理解带来了显著挑战。为应对这些挑战,我们提出了Pharos-ESG统一框架,该框架通过多模态解析、情境化叙述和层级标注,将ESG报告转化为结构化表示。它整合了基于布局流的阅读顺序建模模块、由目录锚点引导的层级感知分割,以及一个将视觉元素情境化转换为连贯自然语言的多模态聚合流程。该框架进一步融合ESG、GRI及情感标签,生成与金融研究分析需求对齐的标注结果。在标注基准上的大量实验表明,Pharos-ESG在表现上持续优于专用文档解析系统和通用多模态模型。此外,我们发布了首个ESG报告大规模公开数据集Aurora-ESG,覆盖中国大陆、香港及美国市场,提供多模态内容的统一结构化表示,并辅以细粒度的布局与语义标注,以更好地支持ESG在金融治理与决策中的整合应用。
https://arxiv.org/abs/2511.16417
We introduce a new agentic artificial intelligence (AI) platform for portfolio management. Our architecture consists of three layers. First, two large language model (LLM) agents are assigned specialized tasks: one agent screens for firms with desirable fundamentals, while a sentiment analysis agent screens for firms with desirable news. Second, these agents deliberate to generate and agree upon buy and sell signals from a large portfolio, substantially narrowing the pool of candidate assets. Finally, we apply a high-dimensional precision matrix estimation procedure to determine optimal portfolio weights. A defining theoretical feature of our framework is that the number of assets in the portfolio is itself a random variable, realized through the screening process. We introduce the concept of sensible screening and establish that, under mild screening errors, the squared Sharpe ratio of the screened portfolio consistently estimates its target. Empirically, our method achieves superior Sharpe ratios relative to an unscreened baseline portfolio and to conventional screening approaches, evaluated on S&P 500 data over the period 2020--2024.
我们推出了一款用于投资组合管理的全新智能体人工智能(AI)平台。该平台架构包含三层:首先,两个大语言模型(LLM)智能体被分配专门任务——一个智能体筛选基本面良好的公司,另一个情感分析智能体则筛选新闻表现良好的公司;其次,这些智能体进行协商以生成并统一对大型投资组合的买卖信号,从而大幅缩小候选资产池;最后,我们采用高维精度矩阵估计方法来确定最优投资组合权重。本框架的一个关键理论特征是:投资组合中的资产数量本身是一个随机变量,通过筛选过程实现。我们提出了“合理筛选”的概念,并证明在温和的筛选误差下,筛选后投资组合的夏普比率平方能一致估计其目标值。实证方面,基于2020至2024年标普500数据评估,我们的方法相较于未筛选基准组合及传统筛选方法,取得了更优的夏普比率。
https://arxiv.org/abs/2603.23300
Language models increasingly "show their work" by writing step-by-step reasoning before answering. But are these reasoning steps genuinely used, or decorative narratives generated after the model has already decided? Consider: a medical AI writes "The patient's eosinophilia and livedo reticularis following catheterization suggest cholesterol embolization syndrome. Answer: B." If we remove the eosinophilia observation, does the diagnosis change? For most frontier models, the answer is no - the step was decorative. We introduce step-level evaluation: remove one reasoning sentence at a time and check whether the answer changes. This simple test requires only API access -- no model weights -- and costs approximately $1-2 per model per task. Testing 10 frontier models (GPT-5.4, Claude Opus, DeepSeek-V3.2, MiniMax-M2.5, Kimi-K2.5, and others) across sentiment, mathematics, topic classification, and medical QA (N=376-500 each), the majority produce decorative reasoning: removing any step changes the answer less than 17% of the time, while any single step alone recovers the answer. This holds even on math, where smaller models (0.8-8B) show genuine step dependence (55% necessity). Two models break the pattern: MiniMax-M2.5 on sentiment (37% necessity) and Kimi-K2.5 on topic classification (39%) - but both shortcut other tasks. Faithfulness is model-specific and task-specific. We also discover "output rigidity": on the same medical questions, Claude Opus writes 11 diagnostic steps while GPT-OSS-120B outputs a single token. Mechanistic analysis (attention patterns) confirms that CoT attention drops more in late layers for decorative tasks (33%) than faithful ones (20%). Implications: step-by-step explanations from frontier models are largely decorative, per-model per-domain evaluation is essential, and training objectives - not scale - determine whether reasoning is genuine.
语言模型越来越多地通过逐步推理来“展示其思考过程”,但这些推理步骤是真正被使用,还是模型早已决定答案后生成的装饰性叙述?考虑以下案例:一个医疗AI写道“患者导管置入后出现嗜酸性粒细胞增多和网状青斑,提示胆固醇栓塞综合征。答案:B。”若移除嗜酸性粒细胞增多的观察,诊断会改变吗?对于大多数前沿模型,答案是否定的——该步骤纯属装饰。我们提出步骤级评估方法:每次移除一个推理句子,检查答案是否变化。这一简单测试仅需API访问权限(无需模型权重),每个模型每项任务成本约1-2美元。我们在情感分析、数学、主题分类和医疗问答(每类任务N=376-500)中测试了10个前沿模型(GPT-5.4、Claude Opus、DeepSeek-V3.2、MiniMax-M2.5、Kimi-K2.5等),发现多数模型产生装饰性推理:移除任意步骤后答案改变的概率低于17%,而任意单步本身即可恢复答案。即使在数学领域,小型模型(0.8-8B)仍表现出真实的步骤依赖性(55%的必要性)。两个模型例外:MiniMax-M2.5在情感分析中(37%必要性)和Kimi-K2.5在主题分类中(39%)——但两者在其他任务中均存在捷径现象。忠实度具有模型特定性和任务特定性。我们还发现“输出刚性”现象:针对相同医疗问题,Claude Opus生成11个诊断步骤,而GPT-OSS-120B仅输出一个标记。机制分析(注意力模式)证实,装饰性任务的思维链注意力在深层下降更显著(33%),而忠实任务仅下降20%。启示:前沿模型的逐步解释大多具有装饰性,必须进行模型与领域特定的评估,且训练目标——而非模型规模——决定推理是否真实。
https://arxiv.org/abs/2603.22816
Users often rely on Large Language Models (LLMs) for processing multiple documents or performing analysis over a number of instances. For example, analysing the overall sentiment of a number of movie reviews requires an LLM to process the sentiment of each review individually in order to provide a final aggregated answer. While LLM performance on such individual tasks is generally high, there has been little research on how LLMs perform when dealing with multi-instance inputs. In this paper, we perform a comprehensive evaluation of the multi-instance processing (MIP) ability of LLMs for tasks in which they excel individually. The results show that all LLMs follow a pattern of slight performance degradation for small numbers of instances (approximately 20-100), followed by a performance collapse on larger instance counts. Crucially, our analysis shows that while context length is associated with this degradation, the number of instances has a stronger effect on the final results. This finding suggests that when optimising LLM performance for MIP, attention should be paid to both context length and, in particular, instance count.
用户通常依赖大语言模型(LLMs)处理多份文档或对多个实例进行分析。例如,分析若干影评的整体情感需要LLM逐一处理每条评论的情感,以提供最终的汇总答案。尽管LLM在单任务上的表现通常良好,但关于其处理多实例输入时的性能研究较少。本文针对LLM在单任务中表现优异的场景,对其多实例处理(MIP)能力进行了全面评估。结果表明,所有LLM均呈现轻微性能下降的模式(实例数约20-100个),随后在实例数量更大时出现性能崩溃。关键的是,我们的分析显示:虽然上下文长度与这种性能下降相关,但实例数量对最终结果的影响更为显著。这一发现表明,在优化LLM的MIP性能时,应同时关注上下文长度,尤其需重视实例数量。
https://arxiv.org/abs/2603.22608
Authors often struggle to interpret peer review feedback, deriving false hope from polite comments or feeling confused by specific low scores. To investigate this, we construct a dataset of over 30,000 ICLR 2021-2025 submissions and compare acceptance prediction performance using numerical scores versus text reviews. Our experiments reveal a significant performance gap: score-based models achieve 91% accuracy, while text-based models reach only 81% even with large language models, indicating that textual information is considerably less reliable. To explain this phenomenon, we first analyze the 9% of samples that score-based models fail to predict, finding their score distributions exhibit high kurtosis and negative skewness, which suggests that individual low scores play a decisive role in rejection even when the average score falls near the borderline. We then examine why text-based accuracy significantly lags behind scores from a review sentiment perspective, revealing the prevalence of the Politeness Principle: reviews of rejected papers still contain more positive than negative sentiment words, masking the true rejection signal and making it difficult for authors to judge outcomes from text alone.
https://arxiv.org/abs/2604.14162
Analyzing news coverage in multilingual societies can offer valuable insights into the dynamics of public discourse and the development of collective narratives, yet comprehensive studies that account for linguistic and cultural diversity within national media ecosystems remain limited, particularly in complex contexts such as Switzerland. This paper studies temporal trends in Swiss digital media across the country's three main linguistic regions, French, German, and Italian, using a triangulated methodology that combines quantitative analyses with qualitative insights. We collected and processed over 1.7 million news articles, applying lexical metrics, named entity recognition and Wikidata-based linking, targeted sentiment analysis, and consensus-based change-point detection. To enable principled cross-language comparisons and to connect to theories of domestication and cultural proximity, we derive domestication profiles together with a proximity salience ratio. Our analysis spans thematic, recurrent, and singular events. By integrating quantitative data with qualitative interpretation, we provide new insights into the dynamics of Swiss digital media and demonstrate the usefulness of triangulation in media studies. The findings reveal distinct temporal patterns and highlight how linguistic and cultural contexts influence reporting. Our approach offers a framework applicable to other multilingual or culturally diverse media environments, contributing to a deeper understanding of how news is shaped by linguistic and cultural factors.
在多语言社会中分析新闻报道能够为公共话语的动态演变和集体叙事的形成提供宝贵洞见,然而,考虑到国家媒体生态系统中语言与文化多样性的综合研究仍然有限,尤其在瑞士这类复杂语境下尤为如此。本研究采用三角验证法,结合量化分析与质性洞察,考察瑞士三大主要语言区(法语区、德语区、意大利语区)数字媒体的时序趋势。我们收集并处理了超过170万篇新闻文章,运用词汇度量、命名实体识别与基于Wikidata的链接技术、定向情感分析以及基于共识的变点检测方法。为进行严谨的跨语言比较并关联本土化理论与文化邻近性理论,我们推导出本土化特征与邻近性显著度比率。分析涵盖主题性事件、周期性事件与突发性事件。通过整合量化数据与质性解读,我们为瑞士数字媒体的动态提供了新见解,并展示了三角验证法在媒体研究中的实用性。研究发现揭示了不同的时序模式,并凸显出语言文化背景如何影响报道方式。本研究提出的分析框架可适用于其他多语言或文化多元的媒体环境,有助于深化理解新闻如何被语言文化因素所塑造。
https://arxiv.org/abs/2603.21519
This paper proposes a refutation-validated framework for aspect-based sentiment analysis in financial markets, addressing the limitations of correlational studies that cannot distinguish genuine associations from spurious ones. Using X data for the energy sector, we test whether aspect-level sentiment signals show robust, refutation-validated relationships with equity returns. Our pipeline combines net-ratio scoring with z-normalization, OLS with Newey West HAC errors, and refutation tests including placebo, random common cause, subset stability, and bootstrap. Across six energy tickers, only a few associations survive all checks, while renewables show aspect and horizon specific responses. While not establishing causality, the framework provides statistically robust, directionally interpretable signals, with limited sample size (six stocks, one quarter) constraining generalizability and framing this work as a methodological proof of concept.
本文提出了一种用于金融市场方面级情感分析的反驳验证框架,以解决相关性研究无法区分真实关联与虚假关联的局限性。利用能源板块的X数据,我们检验了方面级情感信号是否与股票收益率存在稳健的、经反驳验证的关系。我们的流程结合了净比率评分与z标准化、采用Newey West异方差与自相关一致标准误的OLS回归,以及包括安慰剂检验、随机共同原因检验、子集稳定性检验和自助法在内的反驳测试。在六个能源股票中,仅有少数关联通过了所有检验,而可再生能源板块则表现出特定方面和时段的响应。尽管该框架未确立因果关系,但提供了统计稳健且方向可解释的信号。受限于样本量(六只股票、一个季度),研究结果的普适性有限,因此本文可视为方法概念验证。
https://arxiv.org/abs/2603.21473
Human annotation is central to NLP evaluation, yet subjective tasks often exhibit substantial variability across annotators. While large language models (LLMs) can provide structured reasoning to support annotation, their influence on human annotation behavior remains unclear. We introduce ReasonAlign, a reasoning-based annotation scaffold that exposes LLM-generated explanations while withholding predicted labels. We frame this as a controlled study of how reasoning affects human annotation behavior, rather than a full evaluation of annotation accuracy. Using a two-pass protocol inspired by Delphi-style revision, annotators first label instances independently and then revise their decisions after viewing model-generated reasoning. We evaluate the approach on sentiment classification and opinion detection tasks, analyzing changes in inter-annotator agreement and revision behavior. To quantify these effects, we introduce the Annotator Effort Proxy (AEP), a metric capturing the proportion of labels revised after exposure to reasoning. Our results show that exposure to reasoning is associated with increased agreement alongside minimal revision, suggesting that reasoning primarily helps resolve ambiguous cases without inducing widespread changes. These findings provide insight into how reasoning explanations shape annotation consistency and highlight reasoning-based scaffolds as a practical mechanism for supporting human-AI annotation workflows.
人类标注是自然语言处理评估的核心环节,但主观性任务在标注者间常存在显著差异。尽管大语言模型能提供结构化推理以辅助标注,但其对人类标注行为的影响尚不明确。我们提出ReasonAlign——一种基于推理的标注支架,该支架展示大语言模型生成的解释但隐藏预测标签。我们将此设计为一项受控研究,旨在探究推理如何影响人类标注行为,而非对标注准确性进行全面评估。研究采用受德尔斐式修订启发的双轮协议:标注者首先独立标注实例,随后在查看模型生成的推理后修订决策。我们在情感分类与观点检测任务中评估该方法,分析标注者间一致性与修订行为的变化。为量化这些效应,我们引入标注者努力代理指标(AEP),该指标捕捉标注者在接触推理后修订标签的比例。结果表明,接触推理与更高的一致性及最小的修订行为相关,暗示推理主要帮助解决模糊案例,而未引发广泛改动。这些发现揭示了推理解释如何塑造标注一致性,并凸显基于推理的支架可作为支持人机协同标注流程的实用机制。
https://arxiv.org/abs/2603.21094
This paper studies whether a lightweight trained aggregator can combine diverse zero-shot large language model judgments into a stronger downstream signal for corporate disclosure classification. Zero-shot LLMs can read disclosures without task-specific fine-tuning, but their predictions often vary across prompts, reasoning styles, and model families. I address this problem with a multi-agent framework in which three zero-shot agents independently read each disclosure and output a sentiment label, a confidence score, and a short rationale. A logistic meta-classifier then aggregates these signals to predict next-day stock return direction. I use a sample of 18,420 U.S. corporate disclosures issued by Nasdaq and S&P 500 firms between 2018 and 2024, matched to next-day stock returns. Results show that the trained aggregator outperforms all single agents, majority vote, confidence-weighted voting, and a FinBERT baseline. Balanced accuracy rises from 0.561 for the best single agent to 0.612 for the trained aggregator, with the largest gains in disclosures combining strong current performance with weak guidance or elevated risk. The results suggest that zero-shot LLM agents capture complementary financial signals and that supervised aggregation can turn cross-agent disagreement into a more useful classification target.
本文研究轻量级训练聚合器能否将多样化的零样本大语言模型判断整合为更强的企业披露分类下游信号。零样本大语言模型无需任务特定微调即可阅读披露文件,但其预测结果常因提示词、推理方式和模型架构不同而产生差异。本文通过多智能体框架解决此问题:三个零样本智能体独立阅读每份披露文件,分别输出情感标签、置信度评分及简要推理依据,随后逻辑回归元分类器聚合这些信号以预测次日股价涨跌方向。研究采用2018至2024年间纳斯达克及标普500企业发布的18,420份美国企业披露文件样本,并与次日股价回报进行匹配。结果表明,训练聚合器表现优于所有单一智能体、多数投票、置信度加权投票及FinBERT基线模型。平衡准确率从最佳单一智能体的0.561提升至训练聚合器的0.612,其中在同时呈现强劲当前业绩与薄弱指引或较高风险的披露文件中提升最为显著。研究证实零样本大语言模型智能体可捕捉互补性金融信号,且监督聚合能将跨智能体分歧转化为更有效的分类目标。
https://arxiv.org/abs/2603.20965
From customer feedback to social media, understanding human sentiment in text is central to how machines can interact meaningfully with people. However, despite notable progress, accurately capturing sentiment remains a challenging task, which continues to motivate further research in this area. To this end, we introduce Non-Differential Transformer (NDT). It is inspired by (but in contrast to) the state-of-the-art Differential Transformer (DT) model. While standard Transformers can struggle with irrelevant context, the sota DT model uses attention map subtraction, potentially for noise cancellation. We explore an alternative motivation, hypothesizing that benefits may arise from enabling different attention components to specialize on distinct concepts within the text, similar to multiplexing information channels or mixture models, rather than primarily canceling noise via subtraction. Guided by this concept-multiplexing (ConPlex) view, the specific architecture presented in this paper employs a purely additive strategy. It uses only positive weights, learned during training, to ensure constructive combination of these specialized attention perspectives. This design choice explores positive only integration, though our broader framework also shows promise with less constrained linear combinations involving both positive and negative weights. Our model computes attention via this positively weighted sum of multiple distinct attention maps. This allows the model to constructively integrate diverse signals and potentially capture more complex contextual relationships. Competitive performance is achieved by the proposed model for Sentiment Analysis while tested on multiple datasets. We conclude by presenting our results, challenges and future research agenda in this important area of research.
从客户反馈到社交媒体,理解文本中的人类情感是机器与人进行有意义互动的核心。尽管已取得显著进展,但准确捕捉情感仍是一项具有挑战性的任务,持续推动着该领域的进一步研究。为此,我们提出了非差分Transformer(NDT)。其灵感来源于(但区别于)最先进的差分Transformer(DT)模型。标准Transformer可能难以处理无关上下文,而最先进的DT模型则采用注意力图相减的方式,可能用于消除噪声。我们探索了另一种动机,假设其优势可能源于使不同的注意力组件专门处理文本中的不同概念,类似于信息通道的多路复用或混合模型,而非主要通过相减来消除噪声。受此概念复用(ConPlex)观点指导,本文提出的具体架构采用纯加性策略。它仅使用训练过程中学习的正权重,以确保这些专业化注意力视角的建设性组合。这一设计选择探索了仅正数整合的方式,尽管我们更广泛的框架也展示了在涉及正负权重的更宽松线性组合上的潜力。我们的模型通过多个不同注意力图的正权重求和来计算注意力,这使得模型能够建设性地整合多样化信号,并可能捕捉更复杂的上下文关系。所提出的模型在多个数据集的情感分析测试中取得了具有竞争力的性能。最后,我们在此重要研究领域呈现了研究结果、挑战及未来研究计划。
https://arxiv.org/abs/2603.20704
The Hyperspace Analogue to Language (HAL) model relies on global word co-occurrence matrices to construct distributional semantic representations. While these representations capture lexical relationships effectively, aggregating them into sentence-level embeddings via standard mean pooling often results in information loss. Mean pooling assigns equal weight to all tokens, thereby diluting the impact of contextually salient words with uninformative structural tokens. In this paper, we address this limitation by integrating a learnable, temperature-scaled additive attention mechanism into the HAL representation pipeline. To mitigate the sparsity and high dimensionality of the raw co-occurrence matrices, we apply Truncated Singular Value Decomposition (SVD) to project the vectors into a dense latent space prior to the attention layer. We evaluate the proposed architecture on the IMDB sentiment analysis dataset. Empirical results demonstrate that the attention-based pooling approach achieves a test accuracy of 82.38%, yielding an absolute improvement of 6.74 percentage points over the traditional mean pooling baseline (75.64%). Furthermore, qualitative analysis of the attention weights indicates that the mechanism successfully suppresses stop-words and selectively attends to sentiment-bearing tokens, improving both classification performance and model interpretability.
超空间语言类比(HAL)模型依赖全局词共现矩阵构建分布语义表示。尽管这些表示能有效捕捉词汇关系,但通过标准均值池化聚合为句子级嵌入时往往导致信息损失。均值池化对所有词元赋予相同权重,从而稀释了语境显著词汇的影响,同时放大了无信息量的结构词元的作用。本文针对这一局限,在HAL表示流程中集成了可学习的温度缩放可加注意力机制。为缓解原始共现矩阵的稀疏性与高维问题,我们在注意力层前采用截断奇异值分解(SVD)将向量投影至稠密潜在空间。所提架构在IMDB情感分析数据集上进行了评估。实证结果表明,基于注意力池化的方法达到82.38%的测试准确率,相较于传统均值池化基线(75.64%)实现了6.74个百分点的绝对提升。此外,对注意力权重的定性分析显示,该机制成功抑制了停用词,并选择性地聚焦于携带情感信息的词元,从而提升了分类性能与模型可解释性。
https://arxiv.org/abs/2603.20149
Multilingual encoder-based language models are widely adopted for code-mixed analysis tasks, yet we know surprisingly little about how they represent code-mixed inputs internally - or whether those representations meaningfully connect to the constituent languages being mixed. Using Hindi-English as a case study, we construct a unified trilingual corpus of parallel English, Hindi (Devanagari), and Romanized code-mixed sentences, and probe cross-lingual representation alignment across standard multilingual encoders and their code-mixed adapted variants via CKA, token-level saliency, and entropy-based uncertainty analysis. We find that while standard models align English and Hindi well, code-mixed inputs remain loosely connected to either language - and that continued pre-training on code-mixed data improves English-code-mixed alignment at the cost of English-Hindi alignment. Interpretability analyses further reveal a clear asymmetry: models process code-mixed text through an English-dominant semantic subspace, while native-script Hindi provides complementary signals that reduce representational uncertainty. Motivated by these findings, we introduce a trilingual post-training alignment objective that brings code-mixed representations closer to both constituent languages simultaneously, yielding more balanced cross-lingual alignment and downstream gains on sentiment analysis and hate speech detection - showing that grounding code-mixed representations in their constituent languages meaningfully helps cross-lingual understanding.
基于多语言编码器的语言模型被广泛用于代码混合分析任务,然而我们对其内部如何表征代码混合输入,或这些表征是否与混合的组成语言存在有意义的关联,却知之甚少。本文以印地语-英语为案例,构建了一个包含英语、印地语(天城文)及罗马化代码混合句子的统一三语平行语料库,并通过中心核对齐(CKA)、词元级显著性分析及基于熵的不确定性分析,探测标准多语言编码器及其代码混合适配变体间的跨语言表征对齐情况。研究发现:尽管标准模型能良好对齐英语与印地语,但代码混合输入与任一语言的关联均较为松散;且在代码混合数据上持续预训练会以牺牲英语-印地语对齐为代价,提升英语-代码混合对齐。可解释性分析进一步揭示明显的不对称性:模型通过英语主导的语义子空间处理代码混合文本,而原生文字印地语则提供互补信号以降低表征不确定性。基于这些发现,我们提出一种三语后训练对齐目标,使代码混合表征同时贴近两种组成语言,从而实现更均衡的跨语言对齐,并在情感分析与仇恨言论检测任务中获得下游性能提升——表明将代码混合表征锚定于其组成语言,能有效促进跨语言理解。
https://arxiv.org/abs/2603.19771
In the era of large-scale pre-trained models, effectively adapting general knowledge to specific affective computing tasks remains a challenge, particularly regarding computational efficiency and multimodal heterogeneity. While Transformer-based methods have excelled at modeling inter-modal dependencies, their quadratic computational complexity limits their use with long-sequence data. Mamba-based models have emerged as a computationally efficient alternative; however, their inherent sequential scanning mechanism struggles to capture the global, non-sequential relationships that are crucial for effective cross-modal alignment. To address these limitations, we propose \textbf{AlignMamba-2}, an effective and efficient framework for multimodal fusion and sentiment analysis. Our approach introduces a dual alignment strategy that regularizes the model using both Optimal Transport distance and Maximum Mean Discrepancy, promoting geometric and statistical consistency between modalities without incurring any inference-time overhead. More importantly, we design a Modality-Aware Mamba layer, which employs a Mixture-of-Experts architecture with modality-specific and modality-shared experts to explicitly handle data heterogeneity during the fusion process. Extensive experiments on four challenging benchmarks, including dynamic time-series (on the CMU-MOSI and CMU-MOSEI datasets) and static image-related tasks (on the NYU-Depth V2 and MVSA-Single datasets), demonstrate that AlignMamba-2 establishes a new state-of-the-art in both effectiveness and efficiency across diverse pattern recognition tasks, ranging from dynamic time-series analysis to static image-text classification.
https://arxiv.org/abs/2603.18462
This study examines how different artificial intelligence architectures interpret sentiment in conflict-related media discourse, using the 2023 Gaza War as a case study. Drawing on a corpus of 10,990 Arabic news headlines (Eleraqi 2026), the research conducts a comparative analysis between three large language models and six fine-tuned Arabic BERT models. Rather than evaluating accuracy against a single human-annotated gold standard, the study adopts an epistemological approach that treats sentiment classification as an interpretive act produced by model architectures. To quantify systematic differences across models, the analysis employs information-theoretic and distributional metrics, including Shannon Entropy, Jensen-Shannon Distance, and a Variance Score measuring deviation from aggregate model behavior. The results reveal pronounced and non-random divergence in sentiment distributions. Fine-tuned BERT models, particularly MARBERT, exhibit a strong bias toward neutral classifications, while LLMs consistently amplify negative sentiment, with LLaMA-3.1-8B showing near-total collapse into negativity. Frame-conditioned analysis further demonstrates that GPT-4.1 adjusts sentiment judgments in line with narrative frames (e.g., humanitarian, legal, security), whereas other LLMs display limited contextual modulation. These findings suggest that the choice of model constitutes a choice of interpretive lens, shaping how conflict narratives are algorithmically framed and emotionally evaluated. The study contributes to media studies and computational social science by foregrounding algorithmic discrepancy as an object of analysis and by highlighting the risks of treating automated sentiment outputs as neutral or interchangeable measures of media tone in contexts of war and crisis.
https://arxiv.org/abs/2604.08566
We present a practical, reproducible framework for identifying undervalued football players grounded in objective mispricing. Instead of relying on subjective expert labels, we estimate an expected market value from structured data (historical market dynamics, biographical and contract features, transfer history) and compare it to the observed valuation to define mispricing. We then assess whether news-derived Natural Language Processing (NLP) features (i.e., sentiment statistics and semantic embeddings from football articles) complement market signals for shortlisting undervalued players. Using a chronological (leakage-aware) evaluation, gradient-boosted regression explains a large share of the variance in log-transformed market value. For undervaluation shortlisting, ROC-AUC-based ablations show that market dynamics are the primary signal, while NLP features provide consistent, secondary gains that improve robustness and interpretability. SHAP analyses suggest the dominance of market trends and age, with news-derived volatility cues amplifying signals in high-uncertainty regimes. The proposed pipeline is designed for decision support in scouting workflows, emphasizing ranking/shortlisting over hard classification thresholds, and includes a concise reproducibility and ethics statement.
https://arxiv.org/abs/2603.17687