The scarcity of human-annotated literary corpora limits the development of domain-specific sentiment analysis models. This study investigates whether LLM-generated annotations can supervise smaller models for literary sentiment analysis. We fine-tune five BERT models using ordinal regression on 10,889 literary sentences annotated by Gemma 4 31B on a ten-point sentiment scale. The models are evaluated against 1,923 human-annotated sentences from Hemingway's "The Old Man and the Sea", alongside the teacher model and conventional baselines. BERT-large achieves a Kendall's $\tau$ of 0.589, approaching the teacher's 0.604. Although a constant-neutral predictor achieves the lowest overall mean absolute error (MAE), BERT-base outperforms the teacher on non-neutral sentences, achieving an MAE of 0.726 versus 1.116. These findings demonstrate the potential of LLM-generated supervision for developing smaller literary sentiment models, while highlighting the limitations of aggregate error metrics on predominantly neutral datasets.
https://arxiv.org/abs/2611.02985
Classical decompositions of predictive uncertainty, such as the information-theoretic one, are defined for a fixed representation $x$ of the input object. They do not consider that $x$ may be incomplete, nor do they measure how much the missing information can affect the prediction. In Large Language Models, users can clarify an underspecified input without any retraining. The clarified input can describe the user's unobserved intent $z^*$ more accurately and change the predictive uncertainty about the outcome. In this paper, we formalize this setting probabilistically and derive a three-term decomposition of prediction risk into specification, residual aleatoric, and epistemic uncertainties. We show that at the original information level, when only $x$ is available, the aleatoric uncertainty, represented by a Bayes risk, has two components. The first, which we call specification uncertainty, is the expected reduction in this Bayes risk from revealing the intent. The second is the residual aleatoric uncertainty, i.e., the Bayes risk that remains once the intent is known, averaged over its possible values $z$ given $x$. The distinction is important, as specification uncertainty informs the decision to request clarification before making a prediction. We build approximations of these components and connect them to existing uncertainty measures. Our experiments across different domains and modalities show distinct roles for the three components. Specification uncertainty is the most informative for detecting underspecified inputs, while residual aleatoric uncertainty is the most informative for detecting in-distribution prediction errors.
https://arxiv.org/abs/2611.02956
Language model agents increasingly act on users' behalf by manipulating external environments through tools, often from high-level instructions that leave critical task- and environment-specific context unstated. To prevent resulting misaligned actions, recent work verifies proposed actions before execution, largely by establishing whether the conditions supporting them hold. We argue that this confirmation-oriented view leaves a fundamental blind spot: a wrong action often passes every check that asks whether it is right. This motivates a different question for verification: rather than asking what evidence supports an action, can the agent find evidence that refutes it? We pursue this direction with BlackSwan, a refutation-oriented, expect-suspect-test procedure that predicts the intended effect of each state-mutating action, formulates specific and empirically testable hypotheses for how it could be wrong, and tests them using existing observations or additional non-mutating actions, executing the action only if none survives testing. On challenging AppWorld tasks, BlackSwan improves success rate over the strongest baseline by 14.9 and 25.2%p with and without the backbone model's thinking mode, respectively. Even without thinking or in-context demonstrations, it outperforms stronger baselines equipped with them. The gains also transfer beyond AppWorld, with BlackSwan improving WebShop performance by 12.7%p. More broadly, our results suggest that language model agents have an underused capacity to recognize and self-correct misaligned actions, which can be systematically elicited through active conjecture and refutation before execution.
https://arxiv.org/abs/2611.02950
PlagiaCorpus is a bilingual Arabic-English dataset for benchmarking plagiarism and text-reuse detection, including reuse produced by large language models (LLMs) and reuse across languages. It contains 198,643 text records: a source corpus of 34,885 passages drawn from English and Arabic Wikipedia and two openly licensed book collections, and 163,758 queries (147,381 for training and 16,377 for testing). The queries cover five reuse classes of increasing difficulty, namely verbatim copying, character-level obfuscation, same-language paraphrasing by two different LLMs, and English--Arabic translation with structural paraphrasing, together with a Safe class of non-reused passages. Every positive query is linked to its source passage, and the train/test split is grouped by source passage so that no passage contributes queries to both splits. The release was curated through language identification, removal of LLM generation artefacts, and exact and cross-lingual de-duplication. Technical validation reports per-class length statistics, automatic checks of the train/test split, and inter-annotator agreement on a manually rated sample. The dataset is distributed in JSON and Parquet formats under a CC BY-SA 4.0 license.
https://arxiv.org/abs/2611.02940
Long-lived agents rely on persistent memory of users, tasks and decisions, and this memory must stay consistent with a world that keeps changing. When an upstream fact changes, however, memory systems can revise the contradicted memory itself while the beliefs, plans and actions derived from it remain accepted, even though they have lost their support. We therefore formulate dependency-aware state revision, which asks not only what changed but also which dependent states should no longer be trusted. To address it, StateGraph maintains an evolving state dependency graph whose edges are recovered from interaction histories. Its core design is counterfactual verification: each candidate edge is tested by asking whether the dependent state would survive the loss of its premise, which separates support dependence from semantic relatedness, and revision then invalidates a dependent state only when a strict dependency fails and no independent support path survives. To test this design, we introduce StateChangeBench, a controlled benchmark of 50 author-constructed cases annotated with cascade depth, hard negatives and action consequences. On it, StateGraph's Impact-F1 margin over a CUPMem reimplementation is 6.9 percentage points at depth 1 and 26.0 at depth 3+. On public long-term memory benchmarks, its point estimates are comparable to or higher than those of the evaluated baselines on most datasets. These results provide initial evidence that explicit dependency tracking can improve selective memory revision under changing conditions.
https://arxiv.org/abs/2611.02912
Online political discussions increasingly involve AI-mediated participation, as users invoke LLMs to assess contested claims, arbitrate disputes, and respond to opposing viewpoints. As these systems become participants in online exchanges, they may alter which speakers and argumentative strategies receive validation within the discussion. We study this interactional dimension by reconstructing 5,376 this http URL debates as LLM conversations and running nearly 150,000 controlled multi-turn conversations that vary user political orientation, expertise, rhetorical strategy, and defended position, including conversations with competing users. Across naturalistic and controlled debates, we find that LLMs are systematically more receptive to left-leaning than right-leaning users. The asymmetry persists when users with different political orientations defend the same position and when opposing users appear in the same conversation, indicating that it is not fully explained by stance agreement or simple accommodation to the current speaker. Repeated interaction increases receptiveness without eliminating this ordering; expertise also matters, while rhetorical differences are smaller. The pattern appears across multiple models, but is not fixed: fine-tuning on different political corpora can largely erase or reverse it. These results show that LLMs can respond systematically differently to participants in the same political debate, making such interactional asymmetries important for understanding their emerging role in online public discourse.
https://arxiv.org/abs/2611.02908
Recent advancements in sign language processing can be attributed to developments in both large-scale dataset collection and algorithmic complexity in areas such as pose estimation techniques, signal processing through Transformer models, and model optimization. However, only a handful of sign languages, such as the American, British, and German, from over 200 globally recognized sign languages, reap the benefits of such advancements, while the rest lag behind. In this study, we aim to address this technological disparity by proposing a framework for the automatic collection and preparation of sign language datasets, with very minimal human-labour intervention, using the South African Sign Language (SASL) as a testbed. Specifically, we automatically collect SASL video content using public resources such as news broadcasts. Additionally, we convert their accompanying audio streams into text using available Automatic Speech Recognition (ASR) tools. Furthermore, we crop the sign language area in the videos and use gradient descent to locate valleys of non-motion to determine end-of-sentence points within long videos to create our weakly sentence-aligned parallel corpora -- the Maswao (Signs) dataset. Finally, we benchmark the weakly aligned dataset on the task of Sign-to-text Translation using Recurrent Neural Networks and Transformer models to compare their individual intricacies. Our results show that Transformer models proposed in the literature outperform recurrent baselines, with the best-performing Transformer achieving BLEU-1 to BLEU-4 scores of 13.78, 5.21, 2.52, and 1.54, respectively, as well as ChrF = 18.09 and ROUGE-L = 10.51. These results indicate that the task remains promising and warrants further investigations.
https://arxiv.org/abs/2611.02903
Large Language Models (LLMs) are increasingly used in medical question answering (QA) systems. While recent works aim at incrementally improving the downstream task accuracy, an empirical estimation of the models' energy consumption and the associated carbon footprints is often overlooked. In this study, we demonstrate how practitioners can estimate energy consumption and arrive at reliable emission estimates for medical QA tasks available in the OpenMedical-LLM leaderboard by investigating 13 LLMs from 3 model families ranging from 270M to 14B parameters. We discuss how one can critically interpret energy versus accuracy trade-offs for a set of models for a given task. With this work, we underline that reporting disjoint energy and accuracy metrics alone does not suffice for careful trade-off assessments, but it also demands systematic construction and interpretation of joint trade-off metrics. We envisage such studies aiding practitioners in adopting better and more efficient models for their task and helping them become active participants in building sustainable LLM pipelines.
https://arxiv.org/abs/2611.02889
Real-time omnimodal assistants are expected to support people in everyday life, but audiovisual understanding alone does not establish whether they can provide timely and appropriate help. We introduce Omni-Life, a benchmark grounded in real-world user needs, deployment scenarios, and device-dependent observations. It combines controlled video synthesis for hazardous situations and edge cases with annotated real-world videos under a shared temporal protocol. The benchmark contains 400 videos: 290 requiring assistance, with 555 required intervention events, and 110 requiring silence throughout to test whether models can withhold unnecessary responses when no assistance is needed. We evaluate twelve configurations featuring mainstream real-time omnimodal models, jointly assessing event coverage, response content, timing, and unwanted output. At most 4.48% of videos requiring assistance are handled completely correctly. To examine practical deployment strategies, we study task reminders and response-latency tolerance. Reminders can improve recall by 17.12 percentage points but add approximately 4.6 unwanted responses per minute of reference silence. Increasing latency tolerance by 10s improves recall by at most 5.95 percentage points. These results show that existing models remain insufficient to deliver reliable assistance in real-life applications, calling for tailored model optimization in instruction following, timely proactive intervention, and withholding responses when assistance is not needed.
https://arxiv.org/abs/2611.02835
WhatsApp lets a business send free-form messages only within 24 hours of a user's last message; outside this customer service window, only pre-approved templates are delivered. Health chatbots inherit this rule, but its cost is rarely measured. We analyse 98,607 messages sent to 3,696 mothers by a WhatsApp maternal health chatbot in Nigeria, with a largely separate export as replication. No free-form message failed with the window open (0 of 35,500), and failure jumped by 93.0 percentage points (95% CI 87.0 to 99.1) at exactly 24 hours. Two flows produced 66.1% of failures, including an offer to speak with a medical professional that, as built, reached 0.3 in 100 mothers whose window had closed. We formalise window-aware scheduling as a decision problem with an action of known zero value. Model-based offline evaluation, with bounds for unconfirmed delivery, estimates that sending the offer as an approved template would reach 81.5 to 86.8 in 100 such mothers, against 16.6 for waiting and 11.6 for a reply prompt. In a calibrated simulation, tabular Q-learning converges to the same template rule and does not beat it in any of 13 stress tests, and opting out does not rise with message volume. The main gain comes from respecting the platform rule, and it needs no learning. All outcomes are deliveries, not health outcomes.
https://arxiv.org/abs/2611.02834
This paper studies retrieval-augmented generation (RAG), which leverages external knowledge to improve the performance of language models. Despite the remarkable progress, current RAG approaches are still far from satisfactory due to inadequate retrieval and potential hallucinations. Towards this end, we propose a novel approach named Task Refinement with Individual Optimization (TRIO) for RAG. The core idea of our TRIO is to equip three well-designed agents with an iterative refinement paradigm by aligning their individual optimization objectives. Specifically, we first expand ambiguous queries with a query extension agent and quantify the reward based on the improved answer quality, which can be utilized to refine our agent for higher expansion efficiency. To enhance the retrieval quality, we include a unanimity voting to annotate the expanded query as insufficient or sufficient, and their generative outcomes are utilized as ground truth to optimize the judge agent. To further improve evidence utilization and answer accuracy, an answer agent is optimized with dynamic matching-based rewards with curriculum learning for final outputs. Extensive experiments across multiple benchmark datasets validate the effectiveness of the proposed TRIO in comparison with state-of-the-art approaches. Our code is available at this https URL.
https://arxiv.org/abs/2611.02810
Interactive narratives let users shape a story while an Experience Manager (EM) keeps it coherent, balancing player freedom against authorial control. Large Language Models now enable a new generation of hybrid EMs, which combine run-time generation from free-text input with symbolic narrative control. However, their heterogeneity makes them hard to compare: A manager's behaviour is generally tied to the unique and specific scenario in which it operates, and much of its decision-making takes place outside of any explicit and verifiable structure. We address this with an LLM-based narrative platform whose managers are interchangeable modules operating over a shared symbolic world model of facts, operations, and goals. Because every applied operation carries explicit preconditions and effects, each session can be analysed as a plan through a common state-transition representation and evaluated, independently of how the manager works internally, with shared indicators of four properties: player agency, EM controllability, author intent, and robustness. We implement three contrasting managers, based respectively on open generation, Monte Carlo repair, and autonomous characters, and compare them through functional analysis on an interactive Little Red Riding Hood scenario. The results show that no manager dominates on every property, giving authors and EM designers a concrete basis to select a manager according to their priorities.
https://arxiv.org/abs/2611.02807
Recursively self-improving (RSI) systems are increasingly viewed as a promising means of accelerating progress toward artificial general intelligence. They aim to autonomously improve their capabilities by refining their working pipelines and recursively improving the strategies that guide subsequent refinements, with gains generalizing to unseen this http URL, existing evaluations lack reliable metrics to distinguish capability gains from scenario fitting, sustainable and extensible protocols for unseen tasks and difficulties, and fine-grained attribution of improvement to evolution traces. To this end, we propose SelfImprove-Bench,an RSI evaluation framework that organizes tasks into three primary capabilities (i.e., Exploring, Planning, Reasoning) as scenarios for guiding model evolution. We instantiated the tasks on games for controllability and reproducibility, and pairs them with scalable generation and orchestration driven by task templates and difficulty coefficients. Beyond task-level scores, SelfImprove-Bench organizes evaluation into generalization ladder levels G0 to G4 that measure how far gains transfer from training conditions. Experiments reveal that the evolutionary gains of existing RSI methods are inconsistent across generalization levels.
https://arxiv.org/abs/2611.02797
For over 50 years, the database community has developed a wide range of successful engines to answer two fundamental questions: how can database systems run faster, and how can we ensure their correctness? Experience with these engines shows that performance depends on hardware and workloads. As both change over time, we repeatedly redesign and rebuild database systems, a time-consuming and expensive process. Correctness remains another long-standing challenge: recent studies continue to uncover wrong-answer bugs even in mature database engines, despite years of development and testing. To address these, we present GenDB-V, a system that enables AI agents to synthesize database engines specialized to hardware and workloads for performance, and formally verified for correctness. GenDB-V supports specialized implementations of SQL templates and general-purpose engines that accept any query within a supported SQL subset. First, we develop SQLSpec to formalize SQL semantics and deterministically construct fixed, implementation-agnostic synthesis targets. Second, we enable joint synthesis of fast code and formal proofs through storage--execution co-optimization, performance-first exploration, and three-layer modular proofs that bridge low-level execution to SQLSpec semantics. Third, we verify the synthesized code and proofs against the fixed synthesis targets in an isolated pipeline, proving SQL correctness and program safety. We evaluate GenDB-V on TPC-H and SEC-EDGAR. For verified template implementations, GenDB-V achieves geometric-mean speedups of 22.0-61.3x over DuckDB and Umbra. For a verified general-purpose engine, GenDB-V also achieves speedups of 1.27-3.4x on TPC-H. GenDB-V also achieves better performance than a testing-based LLM synthesis method, while our audit and tests expose incorrect answers in that method's implementations for 16 of 28 templates.
https://arxiv.org/abs/2611.02779
Prompt compression is aimed at reducing input prompt lengths to enable cheaper, faster, and potentially higher-quality LLM predictions. However, existing prompt compression methods are often limited by modest compression gains, a risk of hallucination, and/or high compression latency. We propose EffComp, an Efficient prompt Compression framework for RAG-based question answering (QA). EffComp employs BERT-style document reranker and sentence selector models to allow fast extractive prompt compression at the sentence level. Its extractive nature prevents hallucinations in the compressed prompts. Additionally, the training process using a hybrid reinforcement and supervised learning approach is designed to optimize the compression ratio while preserving LLM accuracy. Experiments on various QA datasets demonstrate that EffComp outperforms state-of-the-art prompt compression methods achieving the best trade-off between compression ratio and accuracy with minimal latency. This makes it practical for real-world applications.
https://arxiv.org/abs/2611.02766
Even successful long CoTs may contain harmful supervision, motivating the need for methods that can automatically identify and mask such signals during SFT. Inspired by the MicroMouse maze-solving process, we view a long CoT as a search trajectory from the input problem toward the target answer. This perspective motivates maintaining a goal-relative measure, analogous to a MicroMouse's spatial coordinates, to quantify how close the current reasoning state is to the target answer. Building on this perspective, we propose MicroMouse, an automated selective-SFT framework for masking harmful supervision in long CoTs. In MicroMouse we introduce a Relative Potential (REP) to measure how closely each reasoning state supports the gold answer. Unlike the perplexity of the gold answer alone, REP measures relative support by contrasting the gold answer with a matched foil. This contrast cancels likelihood variations shared by the pair, yielding a more stable signal of progress toward the target answer. By tracking the REP trajectory, MicroMouse identifies consecutive potential decreases as erroneous exploration and post-peak reasoning as redundant wandering, and masks these harmful supervision during SFT. Extensive experiments across multiple student model scales and reasoning benchmarks show that MicroMouse consistently outperforms Full-CoT SFT and existing selective-SFT baselines, yielding average relative gains of 5.5% in greedy accuracy and 2.6% in Pass@1 relative to Full-CoT SFT. Meanwhile, MicroMouse improves reasoning efficiency by reducing average output length by 8.8%, while identifying harmful supervision in only 1.7 seconds per long CoT on average.
https://arxiv.org/abs/2611.02710
Large language models (LLMs) are increasingly used to evaluate candidates for professional roles, raising concerns about their sensitivity to demographic identities. We examine how candidate and evaluator gender assignments affect decisions by LLM-as-a-Judge (LaJ) models and decision language models (DLMs). In a hypothetical city council voting task, eight models evaluated 240 synthetic professional narratives from NVIDIA's US and French Nemotron-Personas datasets under independently varied gender assignments, producing 30,720 judgments. Explicit candidate gender labels increased Yes-vote probability by 1.05-1.73 percentage points relative to unspecified gender, while only the nonbinary evaluator assignment showed a significant increase (1.26 points). Identity matching showed no significant overall association. Yes-vote rates varied across models (81.3-97.2%), and 2.5-3.3% of decisions reversed relative to the unspecified-identity baseline. Under direct substitutions between explicit gender identities, DLMs exhibited fewer decision reversals than LaJ models (1.18% vs. 3.38%), indicating lower observed decision-level gender sensitivity among the tested DLMs. These findings demonstrate that gender sensitivity depends on candidate and evaluator identities and the evaluation model, while highlighting the importance of examining individual decision consistency alongside aggregate differences.
https://arxiv.org/abs/2611.02692
When a masked diffusion language model is sampled in a few parallel steps in a random order, the model actually run is a mixture over reveal plans, while cross-entropy training fits token conditionals rather than this mixture. We introduce mixture-likelihood fine-tuning (Mix-FT), which fine-tunes a pretrained model on an importance-weighted bound of its own sampler's likelihood, with no teacher and no change to the architecture or the sampler. On LLaDA-8B, a LoRA fine-tune for 0.002% of the pretraining compute writes better OpenWebText continuations than continued cross-entropy and Alpha diffusion given the same compute, at every tested step count. With half the model evaluations, 16 rather than 32 steps per block, its continuations score better than the original model's in every seed under three judges, with confidence-based decoding as well as random order, and under confidence-based decoding two blinded LLM raters from different model families prefer them in 69 and 71% of pairs. On a public 110M-parameter block diffusion model, Mix-FT takes under four T4-hours and beats continued cross-entropy, Alpha diffusion and SDTT distillation at 4, 8 and 16 steps per block, under two judges in every seed. Exact likelihoods on text8, with a control that weights every plan equally, attribute about three quarters of the likelihood gain over continued cross-entropy to weighting each plan by how well it explains the sequence.
https://arxiv.org/abs/2611.02666
The author shows a methodology for constructing a network map of the artworld. The tweets posted by a manually comprised set of exemplar artworld actors and Natural Language Processing (NLP) methods are used to identify significant artworld actors, including those that do not own a Twitter account. Identified artworld actors form communities detected with the Louvain method, and their authority is evaluated with the HITS centrality method. The resulting artworld network exhibits the ability, starting with a small set of exemplar actors, to identify new artworld actors and provides a wealth of data that would be very hard to collect otherwise.
https://arxiv.org/abs/2611.02657
Large language models (LLMs) have achieved strong performance across diverse tasks, from question answering to code generation. Recent studies have found that LLMs can perform numerical prediction on tabular datasets via in-context learning. However, it remains unclear under what conditions and how LLMs use variable names and in-context examples for numerical prediction. Here we show that semantic grounding, the match between variable names and the values they describe, allows five LLMs without task-specific training to match or outperform seven supervised machine learning (ML) models across 20 datasets from nine scientific domains, particularly when examples are scarce. Reasoning traces indicate that variable names allow LLMs to draw on domain-specific knowledge acquired during pretraining. Using controlled tasks based on physical formulas, we further show that LLMs integrate domain-specific knowledge with in-context examples in a way consistent with Bayesian updating. Specifically, when the relationship between the inputs and the target cannot be inferred from the examples alone, LLMs rely on domain-specific knowledge as the prior. Conversely, as contradicting examples accumulate, LLM predictions shift progressively towards these examples, which act as the likelihood. Our work reveals how LLMs use domain-specific knowledge in numerical prediction and positions them as data-efficient predictors for data-scarce scientific domains.
https://arxiv.org/abs/2611.02637