Findings of ACL. ACL最新文献

A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends. 基于mlm的视觉丰富文档理解研究：方法、挑战和新趋势。

Findings of ACL. ACL Pub Date : 2026-07-01 DOI: 10.18653/v1/2026.findings-acl.652

Yihao Ding, Siwen Luo, Yue Dai, Yanbei Jiang, Zechuan Li, Qiang Sun, Geoffrey Martin, Wei Liu, Yifan Peng

{"title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends.","authors":"Yihao Ding, Siwen Luo, Yue Dai, Yanbei Jiang, Zechuan Li, Qiang Sun, Geoffrey Martin, Wei Liu, Yifan Peng","doi":"10.18653/v1/2026.findings-acl.652","DOIUrl":"10.18653/v1/2026.findings-acl.652","url":null,"abstract":"Visually Rich Document Understanding (VRDU) has become a pivotal area of research, driven by the need to automatically interpret documents that contain intricate visual, textual, and structural elements. Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant promise in this domain, including both OCR-based and OCR-free approaches for information extraction from document images. This survey reviews recent advances in MLLM-based VRDU, highlighting emerging trends and promising research directions with a focus on two key aspects: (1) techniques for representing and integrating textual, visual, and layout features; (2) training paradigms, including pretraining, instruction tuning, and training strategies. Moreover, we address challenges such as data scarcity, handling multi-page and multilingual documents, and integrating emerging trends such as Retrieval-Augmented Generation and agentic frameworks. Our analysis offers a roadmap for advancing MLLM-based VRDU toward more scalable, reliable, and adaptable systems.","PeriodicalId":521131,"journal":{"name":"Findings of ACL. ACL","volume":"2026 ","pages":"13319-13340"},"PeriodicalIF":0.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13366356/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148451359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence. 忠诚与安全：在反事实医学证据下评估法学硕士行为。

Findings of ACL. ACL Pub Date : 2026-07-01 DOI: 10.18653/v1/2026.findings-acl.1847

Kaijie Mo, Siddhartha Venkatayogi, Chantal Shaib, Ramez Kouzy, Wei Xu, Byron C Wallace, Junyi Jessy Li

{"title":"Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence.","authors":"Kaijie Mo, Siddhartha Venkatayogi, Chantal Shaib, Ramez Kouzy, Wei Xu, Byron C Wallace, Junyi Jessy Li","doi":"10.18653/v1/2026.findings-acl.1847","DOIUrl":"10.18653/v1/2026.findings-acl.1847","url":null,"abstract":"In high-stakes domains like medicine, it may be generally desirable for models to faithfully adhere to the context provided. But what happens if the context does not align with model priors or safety protocols? In this paper, we investigate how LLMs behave and reason when presented with counterfactual (or even adversarial) medical evidence. We first construct MedCounterFact, a counterfactual medical QA dataset that requires the models to answer clinical comparison questions (i.e., judge the efficacy of certain treatments, with evidence consisting of randomized controlled trials provided as context). In MedCounterFact, real-world medical interventions within the questions and evidence are systematically replaced with four types of counterfactual stimuli, ranging from unknown words to toxic substances. Our evaluation across multiple frontier LLMs on MedCounterFact reveals that in the presence of counterfactual evidence, existing models overwhelmingly accept such \"evidence\" at face value even when it is dangerous or implausible, and provide confident and uncaveated answers. While it may be prudent to draw a boundary between faithfulness and safety, our findings suggest that models arguably overemphasize the former.","PeriodicalId":521131,"journal":{"name":"Findings of ACL. ACL","volume":"2026 ","pages":"37053-37081"},"PeriodicalIF":0.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13373577/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148475792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine. 少决定，多沟通：论医学端到端事实核查的结构效度。

Findings of ACL. ACL Pub Date : 2026-07-01 DOI: 10.18653/v1/2026.findings-acl.496

Sebastian Joseph, Lily Chen, Barry Wei, Michael Mackert, Iain J Marshall, Paul Pu Liang, Ramez Kouzy, Byron C Wallace, Junyi Jessy Li

{"title":"Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine.","authors":"Sebastian Joseph, Lily Chen, Barry Wei, Michael Mackert, Iain J Marshall, Paul Pu Liang, Ramez Kouzy, Byron C Wallace, Junyi Jessy Li","doi":"10.18653/v1/2026.findings-acl.496","DOIUrl":"10.18653/v1/2026.findings-acl.496","url":null,"abstract":"Technological progress has led to concrete advancements in tasks that were regarded as challenging, such as automatic fact-checking. Interest in adopting these systems for public health and medicine has grown due to the high-stakes nature of medical decisions and challenges in critically appraising a vast and diverse medical literature. Evidence-based medicine connects to every individual, and yet the nature of it is highly technical, rendering the medical literacy of majority users inadequate to sufficiently navigate the domain. Such problems with medical communication ripen the ground for end-to-end fact-checking agents: check a claim against current medical literature and return with an evidence-backed verdict. And yet, such systems remain largely unused. In this position paper, developed with expert input, we present the first study examining how clinical experts verify real claims from social media by synthesizing medical evidence. In searching for this upper-bound, we reveal fundamental challenges in end-to-end fact-checking when applied to medicine: Difficulties connecting claims in the wild to scientific evidence in the form of clinical trials; ambiguities in underspecified claims mixed with mismatched intentions; and inherently subjective veracity labels. We argue that fact-checking should be approached as an interactive communication problem, rather than an end-to-end process. Data and code are available at https://github.com/SebaJoe/decide-less-communicate-more.","PeriodicalId":521131,"journal":{"name":"Findings of ACL. ACL","volume":"2026 ","pages":"10196-10221"},"PeriodicalIF":0.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13373578/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148475795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine. 医学中基于文本知识图的复杂推理的大型语言模型数据集。

Findings of ACL. ACL Pub Date : 2026-07-01 DOI: 10.18653/v1/2026.findings-acl.1793

Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong Yu

{"title":"RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine.","authors":"Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong Yu","doi":"10.18653/v1/2026.findings-acl.1793","DOIUrl":"10.18653/v1/2026.findings-acl.1793","url":null,"abstract":"Answering complex real-world questions in the medical domain often requires accurate retrieval from medical Textual Knowledge Graphs (medical TKGs), as the relational path information from TKGs could enhance the inference ability of Large Language Models (LLMs). However, the main bottlenecks lie in the scarcity of existing medical TKGs, the limited expressiveness of their topological structures, and the lack of comprehensive evaluations of current retrievers for medical TKGs. To address these challenges, we first develop a Dataset for LLMs Complex Reasoning over medical Textual Knowledge Graphs (RiTeK), covering a broad range of topological structures. Specifically, we synthesize realistic user queries integrating diverse topological structures, relational information, and complex textual descriptions. We conduct a rigorous medical expert evaluation process to assess and validate the quality of our synthesized queries. RiTeK also serves as a comprehensive benchmark dataset for evaluating the capabilities of retrieval systems built upon LLMs. By assessing 11 representative retrievers on this benchmark, we observe that existing methods struggle to perform well, revealing notable limitations in current LLM-driven retrieval approaches. These findings highlight the pressing need for more effective retrieval systems tailored for semi-structured data in the medical domain. The dataset is available here.","PeriodicalId":521131,"journal":{"name":"Findings of ACL. ACL","volume":"2026 ","pages":"35985-36001"},"PeriodicalIF":0.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13322668/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148371823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Budget-Aware Routing for Long Clinical Text. 长临床文本的预算意识路由。

Findings of ACL. ACL Pub Date : 2026-07-01 DOI: 10.18653/v1/2026.findings-acl.2114

Khizar Qureshi, Geoffrey Martin, Yifan Peng

{"title":"Budget-Aware Routing for Long Clinical Text.","authors":"Khizar Qureshi, Geoffrey Martin, Yifan Peng","doi":"10.18653/v1/2026.findings-acl.2114","DOIUrl":"10.18653/v1/2026.findings-acl.2114","url":null,"abstract":"A key challenge for large language models is token cost per query and overall deployment cost. Clinical inputs are long, heterogeneous, and often redundant, while downstream tasks are short and high stakes. We study budgeted context selection, where a subset of document units is chosen under a strict token budget so an off-the-shelf generator can meet fixed cost and latency constraints. We cast this as a knapsack-constrained subset selection problem with two design choices, unitization that defines document segmentation and selection that determines which units are kept. We propose RCD, a monotone submodular objective that balances relevance, coverage, and diversity. We compare sentence, section, window, and cluster-based unitization, and introduce a routing heuristic that adapts to the budget regime. Experiments on MIMIC discharge notes, Cochrane abstracts, and L-Eval show that optimal strategies depend on the evaluation setting. Positional heuristics perform best at low budgets in extractive tasks, while diversity-aware methods such as MMR improve LLM generation. Selector choice matters more than unitization, with cluster-based grouping reducing performance and other schemes behaving similarly. ROUGE saturates for LLM summaries, while BERTScore better reflects quality differences. We release our code at https://github.com/stone-technologies/ACL_budget_paper.","PeriodicalId":521131,"journal":{"name":"Findings of ACL. ACL","volume":"2026 ","pages":"42583-42598"},"PeriodicalIF":0.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13378762/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148582160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction. 基于llm的医疗保健预测的高效内存检索。

Findings of ACL. ACL Pub Date : 2026-07-01 DOI: 10.18653/v1/2026.findings-acl.1788

Mingchen Li, Jiatan Huang, Zonghai Yao, Hong Yu

引用次数: 0

Exploiting Tree Structure for Credit Assignment in Reinforcement Learning with Large Language Models. 利用树结构在大型语言模型强化学习中的信用分配。

Findings of ACL. ACL Pub Date : 2026-07-01 DOI: 10.18653/v1/2026.findings-acl.524

Hieu Tran, Zonghai Yao, Hong Yu

{"title":"Exploiting Tree Structure for Credit Assignment in Reinforcement Learning with Large Language Models.","authors":"Hieu Tran, Zonghai Yao, Hong Yu","doi":"10.18653/v1/2026.findings-acl.524","DOIUrl":"10.18653/v1/2026.findings-acl.524","url":null,"abstract":"Reinforcement learning has shown strong promise for strengthening the reasoning ability of large language models (LLMs), but sparse, delayed rewards over long chains make token-level credit assignment a central challenge. Actor-critic methods like PPO provide token-level credit but require training a value network alongside the policy, which introduces complexity and can encourage overfitting. Critic-free alternatives such as GRPO avoid this burden but rely on sequence-level outcomes, distributing a single reward uniformly across tokens and ignoring structural differences between responses. We propose Prefix-to-Tree (P2T), which organizes the sampled responses of a prompt into a prefix tree and computes nonparametric prefix values by aggregating descendant outcomes. Building on this idea, we develop TEMPO (Tree-Estimated Mean Prefix Value for Policy Optimization), a critic-free algorithm that enriches GRPO with branch-aware temporal-difference (TD) corrections. Across Qwen3-1.7B and Qwen3-4B, TEMPO consistently improves both convergence and final performance over PPO and GRPO on in-distribution benchmarks (MATH, MedQA) and out-of-distribution settings (GSM-HARD, AMC23, MedMCQA, MMLU-Medical), achieving higher validation accuracy within comparable wall-clock time.","PeriodicalId":521131,"journal":{"name":"Findings of ACL. ACL","volume":"2026 ","pages":"10795-10810"},"PeriodicalIF":0.0,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13327694/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148379568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Natural Language Processing in Support of Evidence-based Medicine: A Scoping Review. 支持循证医学的自然语言处理：范围综述。

Findings of ACL. ACL Pub Date : 2025-07-01 DOI: 10.18653/v1/2025.findings-acl.1103

Zihan Xu, Haotian Ma, Gongbo Zhang, Yihao Ding, Chunhua Weng, Yifan Peng

{"title":"Natural Language Processing in Support of Evidence-based Medicine: A Scoping Review.","authors":"Zihan Xu, Haotian Ma, Gongbo Zhang, Yihao Ding, Chunhua Weng, Yifan Peng","doi":"10.18653/v1/2025.findings-acl.1103","DOIUrl":"10.18653/v1/2025.findings-acl.1103","url":null,"abstract":"Evidence-based medicine (EBM) is at the forefront of modern healthcare, emphasizing the use of the best available scientific evidence to guide clinical decisions. Due to the sheer volume and rapid growth of medical literature and the high cost of curation, there is a critical need to investigate Natural Language Processing (NLP) methods to identify, appraise, synthesize, summarize, and disseminate evidence in EBM. This survey presents an in-depth review of 129 research studies on leveraging NLP for EBM, illustrating its pivotal role in enhancing clinical decision-making processes. The paper systematically explores how NLP supports the five fundamental steps of EBM - Ask, Acquire, Appraise, Apply, and Assess. The review not only identifies current limitations within the field but also proposes directions for future research, emphasizing the potential for NLP to revolutionize EBM by refining evidence extraction, evidence synthesis, appraisal, summarization, enhancing data comprehensibility, and facilitating a more efficient clinical workflow.","PeriodicalId":521131,"journal":{"name":"Findings of ACL. ACL","volume":"2025 ","pages":"21421-21443"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12665387/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145656682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dual Debiasing for Noisy In-Context Learning for Text Generation. 文本生成环境中噪声学习的双重降噪方法。

Findings of ACL. ACL Pub Date : 2025-07-01 DOI: 10.18653/v1/2025.findings-acl.665

Siqi Liang, Sumyeong Ahn, Paramveer S Dhillon, Jiayu Zhou

{"title":"Dual Debiasing for Noisy In-Context Learning for Text Generation.","authors":"Siqi Liang, Sumyeong Ahn, Paramveer S Dhillon, Jiayu Zhou","doi":"10.18653/v1/2025.findings-acl.665","DOIUrl":"10.18653/v1/2025.findings-acl.665","url":null,"abstract":"In-context learning (ICL) relies heavily on high-quality demonstrations drawn from large annotated corpora. Existing approaches detect noisy annotations by ranking local perplexities, presuming that noisy samples yield higher perplexities than their clean counterparts. However, this assumption breaks down when the noise ratio is high and many demonstrations are flawed. We re-examine the perplexity-based paradigm for text generation under noisy annotations, highlighting two sources of bias in perplexity: the annotation itself and the domain-specific knowledge inherent in large language models (LLMs). To overcome these biases, we introduce a dual-debiasing framework that uses synthesized neighbors to explicitly correct perplexity estimates, yielding a robust Sample Cleanliness Score. This metric uncovers absolute sample cleanliness regardless of the overall corpus noise level. Extensive experiments demonstrate our method's superior noise-detection capabilities and show that its final ICL performance is comparable to that of a fully clean demonstration corpus. Moreover, our approach remains robust even when noise ratios are extremely high.","PeriodicalId":521131,"journal":{"name":"Findings of ACL. ACL","volume":"2025 ","pages":"12855-12868"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12884952/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146159913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Systematic Evaluation of Auto-Encoding and Large Language Model Representations for Capturing Author States and Traits. 用于捕捉作者状态和特征的自动编码和大语言模型表示的系统评价。

Findings of ACL. ACL Pub Date : 2025-07-01 DOI: 10.18653/v1/2025.findings-acl.971

Khushboo Singh, Vasudha Varadarajan, Adithya V Ganesan, August Håkan Nilsson, Nikita Soni, Syeda Mahwish, Pranav Chitale, Ryan L Boyd, Lyle Ungar, Richard N Rosenthal, H Andrew Schwartz

{"title":"Systematic Evaluation of Auto-Encoding and Large Language Model Representations for Capturing Author States and Traits.","authors":"Khushboo Singh, Vasudha Varadarajan, Adithya V Ganesan, August Håkan Nilsson, Nikita Soni, Syeda Mahwish, Pranav Chitale, Ryan L Boyd, Lyle Ungar, Richard N Rosenthal, H Andrew Schwartz","doi":"10.18653/v1/2025.findings-acl.971","DOIUrl":"10.18653/v1/2025.findings-acl.971","url":null,"abstract":"Large Language Models (LLMs) are increasingly used in human-centered applications, yet their ability to model diverse psychological constructs is not well understood. In this study, we systematically evaluate a range of Transformer-LMs to predict psychological variables across five major dimensions: affect, substance use, mental health, sociodemographics, and personality. Analyses span three temporal levels-short daily text responses about current affect, text aggregated over two-weeks, and user-level text collected over two years-allowing us to examine how each model's strengths align with the underlying stability of different constructs. The findings show that mental health signals emerge as the most accurately predicted dimensions (r ≈ 0.6) across all temporal scales. At the daily scale, smaller models like DeBERTa and HaRT often performed better, whereas, at longer scales or with greater context, larger model like Llama3-8B performed the best. Also, aggregating text over the entire study period yielded stronger correlations for outcomes, such as age and income. Overall, these results suggest the importance of selecting appropriate model architectures and temporal aggregation techniques based on the stability and nature of the target variable.","PeriodicalId":521131,"journal":{"name":"Findings of ACL. ACL","volume":"2025 ","pages":"18955-18973"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13556943/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148922443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0