Relation_Extraction
-
Prompt, Plan, Extract: Zero-Shot Agentic LLMs Workflows for Lung Pathology Extraction from Clinical Narratives
2026-06-18 07:00:43Aman Pathak, Cheng Peng, Mengxian Lyu, Ziyi Chen, Reema Solan, Sankalp Talankar, Yasir Khan, Hiren Mehta, Aokun Chen, Yi Guo, Yonghui WuAbstract
Information extraction from pathology reports is essential for cancer staging, tumor registry population. Yet key data remains embedded in narrative reports, making manual extraction labor-intensive and error-prone. Traditional supervised Natural Language Processing pipelines address this through fully supervised Named Entity Recognition and Relation Extraction, but require expensive manual annotation and suffer cascading failures when upstream entities are missed. In this study, we developed a zero-shot, agentic workflow, and evaluated five open-source generative Large Language Models (LLMs) to populate 13 College of American Pathologists synoptic fields from lung resection pathology reports. We compared them against a state-of-the-art supervised GatorTron NER-RE baseline using a novel, registry-aligned evaluation framework. The baseline achieved Micro-F1of 0.960, while the best zero-shot model (GPT-OSS-20B) achieved Micro-F1 of 0.893 (recall: 0.949), accurately extracting complex relations like Pathologic Stage without task-specific training. These results suggest that open-source, zero-shot agentic LLMs are a low-cost solution for extracting lung pathology information.
Abstract (translated)
URL
https://arxiv.org/abs/2606.19852
PDF
-
NEST: Narrative Event Structures in Time for Long Video Understanding
2026-06-18 02:05:14Ali Asgarov, Kaushik Narasimhan, Najibul Haque Sarker, Hani Alomari, Chia-Wei Tang, Anushka Sivakumar, Zaber Ibn Abdul Hakim, Shaurya Mallampati, Chris ThomasAbstract
Recent progress in vision-language models has enabled the processing of increasingly long video sequences, but the ability to handle extended token streams does not translate to understanding of narrative structure in long videos. Existing long video benchmarks focus on needle-in-a-haystack retrieval rather than evaluating how low-level actions form events, how events interact across time, and how narratives progress, for example, whether a model can connect an early setback, such as a job loss to a later relationship breakup, despite long gaps, intervening scenes, or flashbacks that reframe what occurred. We introduce NEST (Narrative Event Structures in Time for Long Video Understanding), a dataset of 1005 full-length movies (avg. 98 minutes), each annotated with 102 multimodal narrative events grounded in visual content, dialogue, and audio. NEST captures multimodal narrative events with structured annotations grounded in visual content, dialogue, and audio, and links them through relations that reflect narrative structure, including temporal ordering, hierarchical composition, and long-range dependencies. We introduce baselines for event trigger detection (ETD), event localization (EL), event argument extraction (EAE), and event relation extraction (ERE). The benchmark is highly challenging for grounded event discovery, with ETD below 8%, EL under 6%, and EAE below 11%. In contrast, ERE is more tractable once events are given, reaching 35.45% F1 zero-shot and 44.42% F1 after fine-tuning.
Abstract (translated)
URL
https://arxiv.org/abs/2606.19706
PDF
-
SAMA: Semantic Anchor-aligned Augmentation for Unified Low-Resource Multimodal Information Extraction
2026-06-17 07:43:33Quanjiang Guo, Chong Mu, Jiazhou Pan, Ming Jia, Ling Tian, Hui Gao, Zhao KangAbstract
Multimodal Information Extraction (MIE)-covering tasks such as Multimodal Named Entity Recognition (MNER), Relation Extraction (MRE), and Event Extraction (MEE)-is essential for understanding multimedia content but remains constrained by severe data scarcity. Although data augmentation is a promising remedy, existing approaches are impeded by coarse cross-modal alignment and fragmented, task-specific designs that fail to exploit shared semantic knowledge. To overcome these limitations, we introduce Semantic Anchor-aligned Multimodal Augmentation (SAMA), a unified framework for generating high-fidelity, task-aware synthetic data. SAMA constructs structured semantic anchors from ground-truth labels to guide a Collaborative Multi-Experts Multimodal Large Language Model (CME-MLLM), which integrates a Universal Adapter for shared semantics with Task-Specific Adapters to produce diverse yet constraint-compliant textual samples. For image synthesis, SAMA employs an Anchor-Preserving Diffusion mechanism that uses anchor-weighted prompts and latent conditioning to maintain critical semantic anchors while diversifying visual contexts. To eliminate the need for manual verification, SAMA further introduces a Dual-Constraint Filtering module that selects synthetic samples based on both cross-modal consistency and anchor fidelity. Extensive experiments across benchmark datasets for MNER, MRE, and MEE demonstrate that SAMA consistently outperforms state-of-the-art augmentation baselines under both fully supervised and low-resource settings, underscoring its versatility, robustness, and effectiveness.
Abstract (translated)
URL
https://arxiv.org/abs/2606.18780
PDF
-
Few-Shot Biomedical Relation Extraction with Large Language Models: A Viable Alternative to Supervised Learning?
2026-06-13 17:37:50Jakob Mraz, Toma\v{z} Curk, Bla\v{z} ZupanAbstract
Biomedical relation extraction (BioRE) is a key step in transforming biomedical literature into structured knowledge. However, most existing approaches rely on supervised models trained on costly annotated datasets, limiting their scalability and adaptability across relation types and domains. We investigate few-shot BioRE using prompt-based learning with large language models (LLMs) and compare two task formulations: pairwise classification, which predicts relations for individual entity pairs, and joint generation, which extracts multiple relations in a single model call. Experiments on the BioREDirect dataset reveal a clear precision-recall trade-off. Pairwise classification achieves higher recall, whereas joint generation is more precise and computationally efficient. The best-performing model achieves a micro-F1 score of 0.44, substantially outperforming previous few-shot results (0.34) while remaining below the supervised baseline (0.56). Much of this gap is attributable to a single ambiguously defined relation type. When evaluated using macro-F1, which better captures performance across relation types in an imbalanced setting, prompt-based approaches outperform the supervised baseline (0.45 vs. 0.38), particularly on rare relation types. These findings highlight the potential of LLMs for BioRE in low-resource settings and underscore the importance of well-defined relation schemas.
Abstract (translated)
URL
https://arxiv.org/abs/2606.15412
PDF
-
Knowledge Graph Enhanced Memory-Augmented Retrieval for Long Context Modeling
2026-06-12 02:48:45Ghadir Alselwi, Basem Suleiman, Hao Xue, Shoaib Jameel, Hakim Hacid, Flora D. Salim, Imran RazzakAbstract
Long-context language modeling requires not only extending context windows but maintaining coherent understanding of entity states and relationships across thousands of tokens -- a challenge that semantic similarity alone cannot address. KGERMAR addresses this by constructing dynamic, context-specific knowledge graphs from input text during inference, enabling domain-adaptive retrieval that leverages both semantic similarity and explicit entity relationships. The framework performs real-time entity and relation extraction to build contextual knowledge graphs, then integrates graph-structural embeddings with textual semantics through a multi-component memory architecture. Three memory banks -- contextual, semantic, and structural -- are maintained with retrieval signals fused via learned weights to capture both surface-level semantics and deeper relational patterns. Evaluated on SlimPajama (84.7K training examples), WikiText-103 (4,358 examples), PG-19 (100 examples), and Proof-pile (46.3K examples), KGERMAR achieves up to 8.5\% lower perplexity and 2--2.5x better memory efficiency than memory-augmented baselines across context lengths from 1K to 32K tokens, with superior in-context learning performance across five NLU tasks. The dynamic knowledge graph construction approach advances memory-augmented language modeling by enabling domain-specific knowledge representation that adapts to input contexts rather than relying on fixed knowledge bases.
Abstract (translated)
URL
https://arxiv.org/abs/2606.14047
PDF
-
EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision
2026-06-01 03:10:37Tianyi Xu, Yaolun Zhang, Xuan Ouyang, Huazheng WangAbstract
Large language models excel at general tasks but underperform smaller supervised models in specialized, high-stakes domains where training labels are costly. We address this regime with EvoPool, an evolutionary multi-agent framework inspired by Darwinian evolution. Three specialized agents iteratively propose executable annotator code, a small validation set provides a fitness signal, and a deterministic gate keeps only annotators that pass viability, diversity, and marginal-contribution checks across generations. Pool votes are mapped to soft training labels by EvoAgg, a text-aware aggregator combining semantic features with annotator-vote features. The authored pool runs at near-zero per-example cost and is 4500 to 31000x faster than LLM annotation on 100K examples. Across 7 of 8 LLM-weak specialized and complex tasks spanning biomedical relation extraction, legal-clause classification, complex reasoning, and dense multi-label biomedical classification, EvoPool beats the strongest LLM annotation baseline by an average +0.141 macro-F1, peaking at +0.301 on ChemProt and +0.265 on PubMed. Code is available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2606.01617
PDF
-
PubMedCausal: A Span-Level Annotated Corpus for Causal Relation Extraction in Biomedical Text
2026-05-27 11:59:17Ifeoluwa Kunle-John, Josiah Paul, Oluwatosin Agbaakin, Peter Aina, Ikenna Odezuligbo, Sydney AnuyahAbstract
Causal relation extraction (CRE) is central to biomedical text mining, but current resources often conflate causal relations with broader associations, restrict annotation to sentence-level examples, or focus mainly on explicit causal cues. This limits their usefulness for evaluating whether models can recover causal claims as they are actually expressed in biomedical text. We introduce PubMedCausal, a span-level annotated corpus for biomedical CRE built from PubMed abstracts. The corpus contains 30,000 paragraph-level rows, including 3,945 causal rows and 6,491 adjudicated cause--effect pairs. Each causal relation is annotated with full-text cause and effect spans, causality type, and sententiality, enabling evaluation of both causal detection and full-span causal extraction. We benchmark discriminative encoders and open-source generative models across detection and extraction settings. For causal detection, biomedical encoders are strongest, with PubMedBERT reaching an F$_1$ score of 0.7391. For span-level extraction, the best generative baseline is DeepSeek-R1-32B with few-shot prompting, reaching a Cosine Pair F$_1$ of 0.6765. We further test transfer learning by evaluating PubMedCausal-trained encoders on external causal relation datasets, showing that the resource supports cross-dataset evaluation. Our results show that biomedical CRE remains difficult under class imbalance, long causal spans, implicit causality, inter-sentential relations, and prompt sensitivity. Code and Data can be found here: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2605.28363
PDF
-
SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
2026-05-22 09:52:43Jiawei He, Mengyu Shi, Chunrong FangAbstract
Joint Entity and Relation Extraction (JERE) is highly susceptible to weak generalization due to low-quality training data. Data augmentation is a common strategy to enhance model generalization across different domains. However, existing data augmentation methods often overlook text relevance and may disrupt semantic structures and dependencies, making it difficult to generate effective augmented data for improving model generalization. In this paper, we propose Structured Semantic Data Augmentation (SSDAU), a novel method designed to preserve the semantic structure of text during augmentation. SSDAU segments text based on entity labels and employs an encoder to capture semantic features of entities through context awareness. It then performs entity semantic restructuring to generate augmented data. To distinguish semantically similar entities, SSDAU fuses contextualized embeddings with traditional similarity scores. To mitigate potential topic ambiguity and information loss, we apply the BERTTopic model to filter out irrelevant topics, ensuring topic consistency. We evaluate SSDAU on datasets with different annotation types and compare its performance on five representative JERE models against seven popular data augmentation baselines. Experiments demonstrate that SSDAU generates semantically consistent data with superior robustness against ambiguity (8.26\% F1 decrease vs.\ 31.91\% for baselines), significantly outperforming all existing methods across all metrics.
Abstract (translated)
URL
https://arxiv.org/abs/2605.23440
PDF
-
SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction
2026-05-20 05:10:18Miaobo Hu, Shuhao Hu, Bokun Wang, Rui Chen, Xin Wang, Xiaobo Guo, Daren Zha, Jun XiaoAbstract
Multimodal IE in social media is difficult because a post may attach multiple images that are weakly related, redundant, or even misleading with respect to the text. In this setting, always-on multimodal fusion wastes computation and can amplify spurious visual cues. The core challenge is to decide, for each candidate span or marked entity pair, whether vision should be consulted at all and, if so, which small subset of images provides trustworthy evidence. We propose SAVER, a selective vision-as-needed framework for multimodal named entity recognition and multimodal relation extraction. SAVER uses a Conformal Groundability Gate (CGG) to estimate span-level visual groundability in MNER, derive pair-level activation in MRE from the two marked entities, and calibrate the activation threshold on a held-out split via a conformal-style procedure with Clopper--Pearson upper bounds. When activated, a submodular relevance--diversity selector chooses a compact evidence subset across images, which is then aggregated by a Set Transformer. An energy-inspired joint scoring head combines text, optional visual evidence, text--image consistency, and sparse routing for entity typing or relation classification. Experiments show that SAVER consistently improves F1 over strong text-only and always-on multimodal baselines, while reducing AURC, increasing activation coverage at a fixed risk level, and lowering FLOPs and P90 latency.
Abstract (translated)
URL
https://arxiv.org/abs/2605.20713
PDF
-
ContextRAG: Extraction-Free Hierarchical Graph Construction for Retrieval-Augmented Generation
2026-05-19 12:08:19Roman Prosvirnin, Sergei Kuznetsov, Seungmin JinAbstract
Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on large language models (LLMs) to extract entities, relations, and summaries during indexing. These calls add token and wall-clock costs that grow with corpus size. We present ContextRAG, a graph RAG system whose graph topology is constructed without LLM-based entity or relation extraction. ContextRAG derives a fuzzy concept graph over chunk embeddings using residual-quantization k-means and Formal Concept Analysis with Lukasiewicz residuated logic. Bridge-like and meet-derived context nodes are induced by soft fuzzy join and meet operations, rather than by LLM-written graph edges. On a 130-task UltraDomain subset, ContextRAG builds its index with 30 LLM calls and 22,073 tokens. In contrast, a local HiRAG reproduction stress test required 870 indexing calls and 3.54M tokens on a 20-task subset before failing during graph construction; linear extrapolation to 130 tasks implies over 23M indexing tokens. ContextRAG obtains 33.6% F1 overall and 36.8% F1 on multi-hop tasks. An activation analysis shows that queries retrieving at least one lattice-derived node in the top five achieve +3.9 percentage points F1 over queries that do not; this association is diagnostic rather than causal.
Abstract (translated)
URL
https://arxiv.org/abs/2605.19735
PDF
-
BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding
2026-05-12 13:01:25Patrick Knab, Orgest Xhelili, Inis Buzi, Drago Andres Guggiana Nilo, Mohd Saquib Khan, Lorenz Kolb, Manuel Scherzer, Kerem Yildirir, Christian Bartelt, Philipp Johannes SchubertAbstract
Scene understanding is central to general physical intelligence, and video is a primary modality for capturing both state and temporal dynamics of a scene. Yet understanding physical processes remains difficult, as models must combine object localization, hand-object interactions, relational parsing, temporal reasoning, and step-level procedural inference. Existing benchmarks usually evaluate these capabilities separately, limiting diagnosis of why models fail on procedural tasks. We introduce BARISTA, a densely annotated egocentric dataset and benchmark of 185 real-world coffee-preparation videos covering fully automatic, portafilter-based, and capsule-based workflows. BARISTA provides verified per-frame scene graphs linking persistent object identities to masks, tracks, boxes, attributes, typed relations, hand-object interactions, activities, and process steps. From these graphs, we derive zero-shot language-based tasks spanning phrase grounding, hand-object interaction recognition, referring, activity recognition, relation extraction, and temporal visual question answering. Experiments reveal strong variation across task families and no consistently dominant model family, positioning BARISTA as a challenging diagnostic benchmark for procedural video understanding. Code and dataset available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.12074
PDF
-
Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence
2026-05-12 00:07:45Ujun Jeong, Saketh Vishnubhatla, Bohan Jiang, Andre Harrison, Adrienne Raglin, Huan LiuAbstract
During disasters, extracting causal relations from social media can strengthen situational awareness by identifying factors linked to casualties, physical damage, infrastructure disruption, and cascading impacts. However, disaster-related posts are often informal, fragmented, and context-dependent, and they may describe personal experiences rather than explicit causal relations. In this work, we examine whether Large Language Models (LLMs) can effectively extract causal relations from disaster-related social media posts. To this end, we (1) propose an expert-grounded evaluation framework that compares LLM-generated causal graphs with reference graphs derived from disaster-specific reports and (2) assess whether the extracted relations are supported by post-event evidence or instead reflect model priors. Our findings highlight both the potential and risks of using LLMs for causal relation extraction in disaster decision-support systems.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11348
PDF
-
GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction
2026-05-11 07:23:49Ihor Stepanov, Oleksandr Lukashov, Mykhailo Shtopko, Vivek KalyanaranganAbstract
Joint named entity recognition (NER) and relation extraction (RE) is a fundamental task in natural language processing for constructing knowledge graphs from unstructured text. While recent approaches treat NER and RE as separate tasks requiring distinct models, we introduce GLiNER-Relex, a unified architecture that extends the GLiNER framework to perform both entity recognition and relation extraction in a single model. Our approach leverages a shared bidirectional transformer encoder to jointly represent text, entity type labels, and relation type labels, enabling zero-shot extraction of arbitrary entity and relation types specified at inference time. GLiNER-Relex constructs entity pair representations from recognized spans and scores them against relation type embeddings using a dedicated relation scoring module. We evaluate our model on four standard relation extraction benchmarks: CoNLL04, DocRED, FewRel, and CrossRE, and demonstrate competitive performance against both specialized relation extraction models and large language models, while maintaining the computational efficiency characteristic of the GLiNER family. The model is released as an open-source Python package with a simple inference API that allows users to specify arbitrary entity and relation type labels at inference time and obtain both entities and relation triplets in a single call. All models and code are publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2605.10108
PDF
-
Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems
2026-04-22 17:19:43Pavel Salovskii (Partenit.io, San Francisco, CA, USA), Iuliia Gorshkova (Partenit.io, San Francisco, CA, USA)Abstract
This paper presents a hybrid architecture for intelligent systems in which large language models (LLMs) are extended with an external ontological memory layer. Instead of relying solely on parametric knowledge and vector-based retrieval (RAG), the proposed approach constructs and maintains a structured knowledge graph using RDF/OWL representations, enabling persistent, verifiable, and semantically grounded reasoning. The core contribution is an automated pipeline for ontology construction from heterogeneous data sources, including documents, APIs, and dialogue logs. The system performs entity recognition, relation extraction, normalization, and triple generation, followed by validation using SHACL and OWL constraints, and continuous graph updates. During inference, LLMs operate over a combined context that integrates vector-based retrieval with graph-based reasoning and external tool interaction. Experimental observations on planning tasks, including the Tower of Hanoi benchmark, indicate that ontology augmentation improves performance in multi-step reasoning scenarios compared to baseline LLM systems. In addition, the ontology layer enables formal validation of generated outputs, transforming the system into a generation-verification-correction pipeline. The proposed architecture addresses key limitations of current LLM-based systems, including lack of long-term memory, weak structural understanding, and limited reasoning capabilities. It provides a foundation for building agent-based systems, robotics applications, and enterprise AI solutions that require persistent knowledge, explainability, and reliable decision-making.
Abstract (translated)
URL
https://arxiv.org/abs/2604.20795
PDF
-
Improving Radio Interferometry Imaging by Explicitly Modeling Cross-Domain Consistency in Reconstruction
2026-04-18 02:46:26Kai Cheng, Ruoqi Wang, Qiong LuoAbstract
Radio astronomy plays a crucial role in understanding the universe, particularly within the realm of non-thermal astrophysics. Images of celestial objects are derived from the signals (called visibility) measured by radio telescopes. Such imaging results, called dirty images, contain artifacts due to factors such as sparsity and therefore require reconstruction to improve imaging quality. Existing methods typically restrict reconstruction to a unimodal domain, either to the dirty image after imaging or to the sparse visibility prior to imaging. Focusing solely on each unimodal reconstruction results in the loss of complementary in-context information in either the visibility or image domain, leading to an incomplete modeling of mutual dependency and consistency. To address these challenges, we propose CDCRec, a multimodal radio interferometric data reconstruction method that explicitly models cross-domain consistency. We design a hierarchical multi-task and multi-stage framework to enhance the exploration of interplays between domains during reconstruction. Our experimental results demonstrate that CDCRec improves imaging performance through enhanced cross-domain correlation extraction. In particular, our self-supervised complementary modeling strategy is better than current methods at interferometric domain translations that rely heavily on recovering dense information from constrained source-domain data.
Abstract (translated)
URL
https://arxiv.org/abs/2604.16794
PDF
-
LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs
2026-04-09 20:34:33Paolo Gajo, Domenic Rosati, Hassan Sajjad, Alberto Barr\'on-Cede\~noAbstract
Relation extraction represents a fundamental component in the process of creating knowledge graphs, among other applications. Large language models (LLMs) have been adopted as a promising tool for relation extraction, both in supervised and in-context learning settings. However, in this work we show that their performance still lags behind much smaller architectures when the linguistic graph underlying a text has great complexity. To demonstrate this, we evaluate four LLMs against a graph-based parser on six relation extraction datasets with sentence graphs of varying sizes and complexities. Our results show that the graph-based parser increasingly outperforms the LLMs, as the number of relations in the input documents increases. This makes the much lighter graph-based parser a superior choice in the presence of complex linguistic graphs.
Abstract (translated)
URL
https://arxiv.org/abs/2604.08752
PDF
-
HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy
2026-04-09 07:55:27Guoqi Ma, Liang Zhang, Hongyao Tu, Hao Fu, Hui Li, Yujie Lin, Longyue Wang, Weihua Luo, Jinsong SuAbstract
Cross-document relation extraction (RE) aims to identify relations between the head and tail entities located in different documents. Existing approaches typically adopt the paradigm of ``\textit{Small Language Model (SLM) + Classifier}''. However, the limited language understanding ability of SLMs hinders further improvement of their performance. In this paper, we conduct a preliminary study to explore the performance of Large Language Models (LLMs) in cross-document RE. Despite their extensive parameters, our findings indicate that LLMs do not consistently surpass existing SLMs. Further analysis suggests that the underperformance is largely attributed to the challenges posed by the numerous predefined relations. To overcome this issue, we propose an LLM-based \underline{H}ierarchical \underline{C}lassification model for cross-document \underline{RE} (HCRE), which consists of two core components: 1) an LLM for relation prediction and 2) a \textit{hierarchical relation tree} derived from the predefined relation set. This tree enables the LLM to perform hierarchical classification, where the target relation is inferred level by level. Since the number of child nodes is much smaller than the size of the entire predefined relation set, the hierarchical relation tree significantly reduces the number of relation options that LLM needs to consider during inference. However, hierarchical classification introduces the risk of error propagation across levels. To mitigate this, we propose a \textit{prediction-then-verification} inference strategy that improves prediction reliability through multi-view verification at each level. Extensive experiments show that HCRE outperforms existing baselines, validating its effectiveness.
Abstract (translated)
URL
https://arxiv.org/abs/2604.07937
PDF
-
A Parameter-Efficient Transfer Learning Approach through Multitask Prompt Distillation and Decomposition for Clinical NLP
2026-04-08 03:52:52Cheng Peng, Mengxian Lyu, Ziyi Chen, Yonghui WuAbstract
Existing prompt-based fine-tuning methods typically learn task-specific prompts independently, imposing significant computing and storage overhead at scale when deploying multiple clinical natural language processing (NLP) systems. We present a multitask prompt distillation and decomposition framework that learns a single shared metaprompt from 21 diverse clinical source tasks and adapts it to unseen target tasks with fewer than 0.05% trainable parameters. Evaluated across five clinical NLP task types (named entity recognition, relation extraction, question answering, natural language inference, and summarization) on 10 held-out target datasets using three backbone models (LLaMA 3.1 8B, Meditron3 8B, gpt-oss 20B), our framework consistently outperforms LoRA by 1.5~1.7% despite using orders of magnitude fewer parameters, and exceeds single-task prompt tuning by 6.1~6.6%. The gpt-oss 20B model achieves the highest overall performance, particularly on clinical reasoning tasks. The strong zero- and few-shot performance demonstrates better transferability of the shared prompt representation.
Abstract (translated)
URL
https://arxiv.org/abs/2604.06650
PDF
-
LLM-based Atomic Propositions help weak extractors: Evaluation of a Propositioner for triplet extraction
2026-04-03 08:31:22Luc Pommeret (STL), Thomas Gerald (LISN), Patrick Paroubek (STL), Sahar Ghannay (STL), Christophe Servan (STL, AMIAD), Sophie Rosset (LISN, STL)Abstract
Knowledge Graph construction from natural language requires extracting structured triplets from complex, information-dense sentences. In this paper, we investigate if the decomposition of text into atomic propositions (minimal, semantically autonomous units of information) can improve the triplet extraction. We introduce MPropositionneur-V2, a small multilingual model covering six European languages trained by knowledge distillation from Qwen3-32B into a Qwen3-0.6B architecture, and we evaluate its integration into two extraction paradigms: entity-centric (GLiREL) and generative (Qwen3). Experiments on SMiLER, FewRel, DocRED and CaRB show that atomic propositions benefit weaker extractors (GLiREL, CoreNLP, 0.6B models), improving relation recall and, in the multilingual setting, overall accuracy. For stronger LLMs, a fallback combination strategy recovers entity recall losses while preserving the gains in relation extraction. These results show that atomic propositions are an interpretable intermediate data structure that complements extractors without replacing them.
Abstract (translated)
从自然语言构建知识图谱需要从复杂、信息密集的句子中提取结构化三元组。本文研究了将文本分解为原子命题（最小、语义自足的信息单元）是否能改进三元组抽取。我们引入了MPropositionneur-V2，一个覆盖六种欧洲语言的小型多语言模型，通过将Qwen3-32B的知识蒸馏至Qwen3-0.6B架构中进行训练，并评估了其整合到两种抽取范式中的效果：以实体为中心（GLiREL）和生成式（Qwen3）。在SMiLER、FewRel、DocRED和CaRB上的实验表明，原子命题有益于较弱的抽取器（GLiREL、CoreNLP、0.6B模型），提高了关系召回率，并在多语言设置中提升了整体准确率。对于更强大的大语言模型，一种回退组合策略在保持关系抽取增益的同时，恢复了实体召回率的损失。这些结果表明，原子命题是一种可解释的中间数据结构，能够补充而非替代抽取器。
URL
https://arxiv.org/abs/2604.02866
PDF
-
WISTERIA: Weak Implicit Signal-based Temporal Relation Extraction with Attention
2026-03-24 15:20:54Duy Dao Do, Ana\"is Halftermeyer, Thi-Bich-Hanh DaoAbstract
Temporal Relation Extraction (TRE) requires identifying how two events or temporal expressions are related in time. Existing attention-based models often highlight globally salient tokens but overlook the pair-specific cues that actually determine the temporal relation. We propose WISTERIA (Weak Implicit Signal-based Temporal Relation Extraction with Attention), a framework that examines whether the top-K attention components conditioned on each event pair truly encode interpretable evidence for temporal classification. Unlike prior works assuming explicit markers such as before, after, or when, WISTERIA considers signals as any lexical, syntactic, or morphological element implicitly expressing temporal order. By combining multi-head attention with pair-conditioned top-K pooling, the model isolates the most informative contextual tokens for each pair. We conduct extensive experiments on TimeBank-Dense, MATRES, TDDMan, and TDDAuto, including linguistic analyses of top-K tokens. Results show that WISTERIA achieves competitive accuracy and reveals pair-level rationales aligned with temporal linguistic cues, offering a localized and interpretable view of temporal reasoning.
Abstract (translated)
时间关系提取（Temporal Relation Extraction, TRE）需要识别两个事件或时间表达式在时间上的关联方式。现有的基于注意力的模型常聚焦于全局显著标记，却忽略了实际决定时间关系的事件对特定线索。我们提出WISTERIA（基于弱隐式信号与注意力机制的时间关系提取）框架，该框架检验了在 conditioning on 每个事件对条件下的top-K注意力成分是否真正编码了可解释的时间分类证据。与先前假设"之前"、"之后"或"当...时"等显性标记的研究不同，WISTERIA将信号定义为任何隐式表达时间顺序的词汇、句法或形态学元素。通过将多头注意力与事件对条件化的top-K池化相结合，模型能为每个事件对分离出最具信息量的上下文标记。我们在TimeBank-Dense、MATRES、TDDMan和TDDAuto数据集上进行了广泛实验，包括对top-K标记的语言学分析。结果表明，WISTERIA实现了具有竞争力的准确率，并揭示了与时间语言学线索对齐的事件级推理依据，为时间推理提供了局部化且可解释的视角。
URL
https://arxiv.org/abs/2603.23319
PDF
