United States

Evaluating the quality of LLM-generated reasoning traces in expert domains (e.g., law) is essential for ensuring credibility and explainability, yet remains challenging due to the inherent complexity of such reasoning tasks. We introduce LEGIT (LEGal Issue Trees), a novel large-scale (24K instances) expert-level legal reasoning dataset with an emphasis on reasoning trace evaluation. We convert court judgments into hierarchical trees of opposing parties&#39; arguments and the court&#39;s conclusions, which serve as rubrics for evaluating the issue coverage and correctness of the reasoning traces. We verify the reliability of these rubrics via human expert annotations and comparison with coarse, less informative rubrics. Using the LEGIT dataset, we show that (1) LLMs&#39; legal reasoning ability is seriously affected by both legal issue coverage and correctness, and that (2) retrieval-augmented generation (RAG) and RL with rubrics bring complementary benefits for legal reasoning abilities, where RAG improves overall reasoning capability, whereas RL improves correctness albeit with reduced coverage.

ACL 2026

Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Evaluating the quality of LLM-generated reasoning traces in expert domains (e.g., law) is essential for ensuring credibility and explainability, yet remains challenging due to the inherent complexity of such reasoning tasks. We introduce LEGIT (LEGal Issue Trees), a novel large-scale (24K instances) expert-level legal reasoning dataset with an emphasis on reasoning trace evaluation. We convert court judgments into hierarchical trees of opposing parties' arguments and the court's conclusions, which serve as rubrics for evaluating the issue coverage and correctness of the reasoning traces. We verify the reliability of these rubrics via human expert annotations and comparison with coarse, less informative rubrics. Using the LEGIT dataset, we show that (1) LLMs' legal reasoning ability is seriously affected by both legal issue coverage and correctness, and that (2) retrieval-augmented generation (RAG) and RL with rubrics bring complementary benefits for legal reasoning abilities, where RAG improves overall reasoning capability, whereas RL improves correctness albeit with reduced coverage.

technical paper

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/acl2026

Registration Required

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

Safety alignment---training large language models (LLMs) to refuse harmful requests while remaining helpful---is critical for responsible deployment. Prior work established that safety behaviors are governed by low-rank structures, suggesting parameter-efficient fine-tuning (PEFT) should be well-suited for alignment. However, Low-Rank Adaptation (LoRA) consistently underperforms full fine-tuning and reinforcement learning on safety benchmarks. We attribute this gap to semantic entanglement: safety-relevant directions are intertwined with unrelated concepts due to polysemanticity, impeding implicit subspace identification. To address this, we propose SAILS (Safety Alignment via Interpretable Low-rank Subspace), which leverages Sparse Autoencoders (SAEs) to disentangle representations into monosemantic features, constructs an interpretable safety subspace from SAE decoder directions, and uses it to initialize LoRA adapters. Theoretically, we prove that SAE-based identification achieves arbitrarily small recovery error under monosemanticity assumptions, while direct identification suffers an irreducible error floor. Empirically, SAILS achieves up to 99.6% safety rates across multiple model families and scales, exceeding full fine-tuning and matching RLHF-based models, with only 0.2% of parameters updated and providing interpretability.

Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation

Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness limits the model's applications in scenarios such as in-context learning and Retrieval-Augmented Generation (RAG). Recent studies attempt to obtain optimal or suboptimal arrangements based on statistical results or using dataset-based search, but these methods increase inference overhead while leaving the model's inherent order bias unresolved. Other studies mitigate order sensitivity through supervised fine-tuning using augmented training sets with multiple order variants, but often at the cost of accuracy, trapping the model in consistent yet incorrect hallucinations. In this paper, we propose \textbf{D}ual \textbf{G}roup \textbf{A}dvantage \textbf{O}ptimization (\textbf{DGAO}), which aims to improve model accuracy and order stability simultaneously. DGAO calculates and balances intra-group relative accuracy advantage and inter-group relative stability advantage, rewarding the policy model for generating order-stable and correct outputs while penalizing order-sensitive or incorrect responses. This marks the first time reinforcement learning has been used to mitigate LLMs' order sensitivity. We also propose two new metrics, Consistency Rate and Overconfidence Rate, to reveal the pseudo-stability of previous methods and guide more comprehensive evaluation. Extensive experiments demonstrate that DGAO achieves superior order fairness while improving performance on RAG, mathematical reasoning, and classification tasks. Our code is available at: \url{https://anonymous.4open.science/r/DGAO-A481/}

Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization

User simulation is increasingly vital to develop and evaluate recommender systems (RSs). While Large Language Models (LLMs) offer promising avenues to simulate user behavior, they often struggle with the absence of specific task alignment required for RSs and the efficiency demands of large-scale simulation. A vast yet underutilized resource for enhancing this alignment is the extensive user feedback inherent in RSs, but leveraging it is challenging due to its ambiguity, noise and massive volume, which hinders efficient preference alignment. To overcome these hurdles, we introduce a novel data construction framework that leverages user feedback in RSs with advanced LLM capabilities to generate high-quality simulation data. Our framework unfolds in two key phases: (1) using LLMs to generate decision-making processes as explanatory rationales on simulation samples, thereby reducing ambiguity; and (2) data distillation based on uncertainty estimation and behavior sampling to efficiently filter the most informative, denoised samples. Accordingly, we fine-tune lightweight LLMs, as user simulators, using such high-quality dataset with corresponding decision-making processes. Extensive experiments confirm that our framework significantly boosts the alignment with human preferences and the in-domain reasoning capabilities of the fine-tuned LLMs, providing more insightful and interpretable signals for RS interaction. We believe our work, together with publicly available developed framework, high-quality mixed-domain dataset, and fine-tuned LLM checkpoints, will advance the RS community and offer valuable insights for broader human-centric AI research. Our code is available at https://github.com/Joinn99/UserMirrorer.

Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation

In many real-world applications, such as medical insurance, many regulations exist that define how data should comply with certain standards. Auditors typically use these regulations to identify anomalies in tabular data. However, existing tabular anomaly detection methods often focus on detecting anomalies based on data distribution without considering regulatory compliance. In this paper, we introduce a new task, Regulation-guided Tabular Anomaly Detection, which leverages regulations to detect anomalies in tabular data. We also developed three new datasets for this task. To address this task, we present RegValidator, a training-free method that integrates data validation with large language models (LLMs) for detecting anomalies. In this process, the LLMs generate ideas for anomaly detection from a regulation perspective, while the data validation validates these ideas from a data distribution perspective. This process can be framed as a Budgeted Maximum Coverage problem, which can be solved by a constant-factor approximation algorithm with provable guarantees. Empirical results on the new datasets demonstrate that our method outperforms existing baselines. A field experiment in a commercial health insurance company also reveals the practical value of our method. Our code is available at https://github.com/hnu-vis/RegValidator.

Integrating Data Validation with Large Language Models for Regulation-Guided Tabular Anomaly Detection

Despite recent progress in LLMs for text style transfer, most existing methods rely on costly task-specific training and offer limited control over separating stylistic modification from content preservation. We propose Diff4TST, a diffusion-based language model that formulates text style transfer as an explicit copy-and-edit process. Built upon masked diffusion language models, Diff4TST introduces a style-aware noise schedule that selectively perturbs stylistic tokens while preserving content-bearing tokens during supervised fine-tuning.
At inference time, we further introduce a generate-then-refine strategy that iteratively improves style compliance via gradient-based token re-masking, without reinforcement learning or external reward models. Extensive experiments on both fine-grained and polarity-based benchmarks show that Diff4TST achieves substantially improved style accuracy and controllability while maintaining strong content preservation and fluency. These results suggest diffusion-based language models as a principled and effective alternative to autoregressive pipelines for text style transfer.

Diff4TST: Masked Diffusion Language Model for Text Style Transfer

Vision-language model (VLM) based web agents demonstrate impressive autonomous GUI interaction but remain vulnerable to deceptive interface elements. Existing approaches either detect deception without task integration or document attacks without proposing defenses. We formalize deception-aware web agent defense and propose DUDE (Deceptive UI Detector & Evaluator), a two-stage framework combining hybrid-reward learning with asymmetric penalties and experience summarization to distill failure patterns into transferable guidance. We introduce RUC (Real UI Clickboxes), a benchmark of 1,407 scenarios spanning four domains and deception categories. Experiments show DUDE reduces deception susceptibility by 53.8% while maintaining task performance, establishing an effective foundation for robust web agent deployment.

Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces

Equipping Large Language Models (LLMs) with pedagogical tutoring capabilities holds significant promise for education. Existing approaches simulate tutor behaviors or preferences and use them to prompt or fine-tune LLMs for dialogue tutoring. However, such methods often fail to sustain high-quality pedagogical conversations that provide explicit stepwise scaffolding and adapt to learners' evolving cognitive states. To address this, we propose ScaffoldLM, a planning-guided tutoring framework with an assessment-driven memory for multi-turn math dialogue tutoring. ScaffoldLM first generates a stepwise pedagogical plan from solution steps, which serves as a stable backbone for explicit scaffolding. During tutoring, the tutoring memory is updated by an assessment-driven control loop that infers the learner’s cognitive state, evaluates whether the current step target is met, and adaptively selects tutoring actions. The plan, step-level progress, inferred learner states, and dialogue history are maintained in memory to support coherent multi-turn guidance. Experiments on multi-turn math tutoring benchmarks demonstrate that ScaffoldLM substantially improves pedagogical tutoring quality over strong baselines. Code is publicly available at https://github.com/BNU-ERC-ITEA/ScaffoldLM.

Planning-Guided Tutoring with Assessment-Driven Memory for Pedagogical LLM Tutors

Chart reasoning is a critical capability for Vision Language Models (VLMs). However, the development of open-source models is severely hindered by the lack of high-quality training data. Existing datasets suffer from a dual challenge: synthetic charts are often simplistic and repetitive, while the associated QA pairs are prone to hallucinations and lack the reasoning depth required for complex tasks. To bridge this gap, we propose **ChartVerse**, a scalable framework designed to synthesize complex charts and reliable reasoning data from scratch. (1) To address the bottleneck of simple patterns, we first introduce **Rollout Posterior Entropy (RPE)**, a novel metric that quantifies chart complexity. Guided by RPE, we develop **complexity-aware chart coder** to autonomously synthesize diverse, high-complexity charts via executable programs. (2) To guarantee reasoning rigor, we develop **truth-anchored inverse QA synthesis**. Diverging from standard generation, we adopt an answer-first paradigm: we extract deterministic answers directly from the source code, generate questions conditional on these anchors, and enforce strict consistency verification. To further elevate difficulty and reasoning depth, we filter samples based on model fail-rate and distill high-quality Chain-of-Thought (CoT) reasoning. We curate ChartVerse-SFT-600K and ChartVerse-RL-40K using Qwen3-VL-30B-A3B-Thinking as the teacher. Experimental results demonstrate that ChartVerse-8B achieves state-of-the-art performance, notably surpassing its teacher and rivaling the stronger Qwen3-32B-Thinking.

 ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch

Lipid nanoparticles (LNPs) can deliver cargos to both tumor and immune cells, playing a crucial role in biomedicine. Traditional approaches rely on experimental screening and expert knowledge, which can be costly and time-consuming. Recent methods based on language models have accelerated this process using deep learning. Although these methods can retrieve molecules for fusion or rank candidates from existing libraries, they are still limited by the scope of known formulations. In this work, we propose a method, LiGen, to generate lipid molecules efficiently and actively, facilitating the discovery of high-performing LNP formulations. We first train a lipid-specific molecular language model, LiCore, to learn hidden representations of lipid molecules. We then explore the learned latent space to generate improved candidate formulations. This process is guided by a trained predictor, which evaluates delivery efficiency and provides directional signals. In reconstruction tasks, LiCore achieves nearly perfect reconstruction output with a low invalid ratio on both the LNP-Virtual900k and LNP-Exp12k datasets. The predictor consistently improves ranking-oriented metrics across multiple cell lines, with our method outperforming the best baselines by an average of 4.1%, 10.8%, and 8.1% in Top-50, Top-10, and Top-5 identification accuracy, respectively. Guided by the predictor, LiGen generates novel lipid candidates that achieve a 30.7% improvement over baseline methods on average, with some samples exceeding 50% improvement.

LiGen: Active Lipid Generation via a Molecular Language Model

Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose this vulnerability, we present **R**ank **A**nything **F**irst (RAF), a two-stage token optimization method that crafts concise textual perturbations to consistently promote a target item in LLM-generated rankings while remaining hard to detect. Stage 1 uses Greedy Coordinate Gradient to shortlist candidate tokens at the current position by combining the gradient of the rank-target with a readability score; Stage 2 evaluates those candidates under exact ranking and readability losses using an entropy-based dynamic weighting scheme, and selects a token via temperature-controlled sampling. RAF generates ranking-promoting prompts token-by-token, guided by dual objectives: maximizing ranking effectiveness and preserving linguistic naturalness. Experiments across multiple LLMs show that RAF significantly boosts the rank of target items using naturalistic language, with greater robustness than existing methods in both promoting target items and maintaining naturalness. These findings underscore a critical security implication: LLM-based reranking is inherently susceptible to adversarial manipulation, raising new challenges for the trustworthiness and robustness of modern retrieval systems. Our code is available at: https://github.com/glad-lab/RAF.

Downloads

Next from ACL 2026

Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation

Similar lecture

CourtReasoner: Can LLM Agents Reason Like Judges?

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL 2026

Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation

Similar lecture

CourtReasoner: Can LLM Agents Reason Like Judges?

Downloads