United States

Most ATP benchmarks embed the final answer within the formal statement — a convention we call &quot;Easy Mode&quot; — a design that simplifies the task relative to what human competitors face and may lead to optimistic estimates of model capability.
We call the stricter, more realistic setting &quot;Hard Mode&quot;: the system must independently discover the answer before constructing a formal proof.
To enable Hard Mode research, we make two contributions.
First, we release MiniF2F-Hard and FIMO-Hard, expert-reannotated Hard Mode variants of two widely-used ATP benchmarks.
Second, we introduce Discover And Prove (DAP), an agentic framework that uses LLM natural-language reasoning with explicit self-reflection to discover answers, then rewrites Hard Mode statements into Easy Mode ones for existing ATP provers.
DAP sets the state of the art: on CombiBench it raises solved problems from 7 (previous SOTA, Pass@16) to 10; on PutnamBench it is the first system to formally prove 36 theorems in Hard Mode — while simultaneously revealing that state-of-the-art LLMs exceed 80% answer accuracy on the same problems where formal provers manage under 10%, exposing a substantial gap that Hard Mode benchmarks are uniquely suited to measure.

ACL 2026

Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Most ATP benchmarks embed the final answer within the formal statement — a convention we call "Easy Mode" — a design that simplifies the task relative to what human competitors face and may lead to optimistic estimates of model capability.
We call the stricter, more realistic setting "Hard Mode": the system must independently discover the answer before constructing a formal proof.
To enable Hard Mode research, we make two contributions.
First, we release MiniF2F-Hard and FIMO-Hard, expert-reannotated Hard Mode variants of two widely-used ATP benchmarks.
Second, we introduce Discover And Prove (DAP), an agentic framework that uses LLM natural-language reasoning with explicit self-reflection to discover answers, then rewrites Hard Mode statements into Easy Mode ones for existing ATP provers.
DAP sets the state of the art: on CombiBench it raises solved problems from 7 (previous SOTA, Pass@16) to 10; on PutnamBench it is the first system to formally prove 36 theorems in Hard Mode — while simultaneously revealing that state-of-the-art LLMs exceed 80% answer accuracy on the same problems where formal provers manage under 10%, exposing a substantial gap that Hard Mode benchmarks are uniquely suited to measure.

poster

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.

Knowledge editing aims to modify outdated knowledge in language models efficiently while retaining their original capabilities. Mainstream datasets for knowledge editing are predominantly static and fail to keep in pace with the evolving real-world knowledge. In this work, we introduce CRAFT, an ever-evolving real-world dataset for knowledge editing. It evaluates models on temporal locality, common-sense locality, composite portability and alias portability, providing a comprehensive and challenging evaluation for knowledge editing, on which previous methods hardly achieve balanced performance. Towards flexible real-time knowledge editing, we propose KEDAS, a novel paradigm of knowledge editing alignment featuring diverse edit augmentation and self-adaptive post-alignment inference, exhibiting significant performance gain on both CRAFT and traditional datasets compared to previous methods. We hope this work may serve as a catalyst for shifting the focus of knowledge editing from static update to dynamic evolution.

 Aligning Language Models with Real-time Knowledge Editing

We introduce SLR, an end-to-end framework for systematic evaluation and training of Large Language Models (LLMs) via Scalable Logical Reasoning. Given a user's task specification, SLR automatically synthesizes (i) an instruction prompt for an inductive reasoning task, (ii) a validation program, executable on model outputs to provide verifiable rewards, and (iii) the latent ground-truth rule. This process is fully automated, scalable, requires no human annotations, and offers precise control over task difficulty. Using SLR, we create SLR-Bench, a benchmark comprising 19k prompts organized into 20 curriculum levels that progressively increase in relational, arithmetic, and recursive complexity. Large-scale evaluation reveals that contemporary LLMs readily produce syntactically valid rules, yet often fail at correct logical inference. Recent reasoning LLMs demonstrate improved performance but incur very high test-time computation, with costs exceeding $300 for just 1,000 prompts. Finally, curriculum learning via SLR doubles Llama-3-8B accuracy on SLR-Bench, achieving parity with Gemini-Flash-Thinking at a fraction of computational cost. Moreover, these reasoning capabilities generalize to a wide range of established benchmarks, underscoring the effectiveness of SLR for downstream reasoning.

SLR: Automated Synthesis for Scalable Logical Reasoning

Video anomaly understanding (VAU) is critical for real-world scenarios. Recent advances in Video Large Language Models (Video-LLMs) enhance the ability of VAU models to describe and interpret anomalies. However, progress in anomaly localization is still limited by two key issues. First, most existing video anomaly datasets only annotate segments that are clearly inconsistent with the context, often omitting subsequent segments that are semantically part of the same abnormal event. Second, the field lacks systematic evaluation protocols. To bridge these gaps, we introduce VALU, a new benchmark that explicitly defines anomalies across five semantic levels and provides comprehensive temporal boundaries and detailed textual descriptions for each. Based on these annotations, we design three evaluation tasks that comprehensively assess models' capabilities across different dimensions, including temporal grounding, anomaly localization, and anomaly detail discrimination. Evaluation results reveal persistent challenges in current models' capabilities on VAU. We further analyze and discuss these findings, and hope that both VALU and insights will advance research in VAU and the development of Video-LLMs. Our benchmark will be publicly available.

VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels

Large language models (LLMs) learn non-trivial abstractions during pretraining, such as detecting irregular plural noun subjects. However, because traditional evaluation methods (e.g., benchmarking) fail to reveal how models acquire these concepts and capabilities, it is not well understood when and how these specific linguistic abilities emerge. To bridge this gap and better understand model training at the concept level, we use sparse crosscoders to discover and align features across model checkpoints. Using this approach, we track the evolution of linguistic features during pretraining. We train crosscoders between open-sourced checkpoint triplets with significant performance and representation shifts, and introduce a novel metric, Relative Indirect Effects (RelIE), to trace training stages at which individual features become causally important for task performance. We show that crosscoders can detect feature emergence, maintenance, and discontinuation during pretraining. Our approach is architecture-agnostic and scalable, offering a promising path toward more interpretable and fine-grained analysis of representation learning throughout pretraining.

 Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining

Web agents have shown great promise in performing many tasks on e-commerce websites. To assess their capabilities, several benchmarks have been introduced. However, current benchmarks in the e-commerce domain face two major problems. First, they primarily focus on product search tasks (e.g., "Find an Apple Watch"), failing to capture the broader range of functionalities offered by real-world e-commerce services such as Amazon, including account management and gift card operations. Second, existing benchmarks typically evaluate whether the agent completes the user query, but ignore the potential risks involved. In practice, web agents can make unintended changes that negatively impact the user’s account or status. For instance, an agent might purchase the wrong item, delete a saved address, or incorrectly configure an auto-reload setting. To address these gaps, we propose a new benchmark called Amazon-Bench. To generate user queries that cover a broad range of tasks, we propose a data generation pipeline that leverages webpage content and interactive elements (e.g., buttons, check boxes) to create diverse, functionality-grounded user queries covering tasks such as address management, wishlist management, and brand store following. To enhance agent evaluation, we propose an automated evaluation framework that assesses both the performance and safety of web agents. We systematically evaluate various agents, finding that current agents struggle with complex queries and pose safety risks. These results highlight the need for developing more robust and reliable web agents.

A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce Domains

To acquire instruction-following capabilities, large language models (LLMs) undergo instruction tuning, where they are trained on instruction-response pairs using next-token prediction (NTP). Efforts to improve instruction tuning often focus on higher-quality supervised fine-tuning (SFT) datasets, typically requiring data filtering with proprietary LLMs or human annotation. In this paper, we take a different approach by proposing SFTMix, a novel Mixup-based recipe that elevates LLM instruction tuning without relying on well-curated datasets. We observe that LLMs exhibit uneven confidence across the semantic representation space. We argue that examples with different confidence levels should play distinct roles in instruction tuning: Confident data is prone to overfitting, while unconfident data is harder to generalize. Based on this insight, SFTMix leverages training dynamics to identify examples with varying confidence levels. We then interpolate them to bridge the confidence gap and apply a Mixup-based regularization to support learning on these additional, interpolated examples. We demonstrate the effectiveness of SFTMix in both instruction-following and healthcare-specific SFT tasks, with consistent improvements across LLM families and SFT datasets of varying sizes and qualities. Extensive analyses across six directions highlight SFTMix's compatibility with data selection, adaptability to compute-constrained scenarios, and scalability to broader applications.

SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe

We present ChatR1, a reasoning framework based on reinforcement learning (RL) for conversational question answering (CQA). Reasoning plays an important role in CQA, where user intent evolves across dialogue turns, and utterances are often underspecified, requiring contextual interpretation, query reformulation, and dynamic coordination between retrieval and generation. Unlike static `rewrite, retrieve, and generate' pipelines, ChatR1 interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through RL. To address the challenge of sparse and delayed rewards in RL, we propose an intent-aware reward that provides turn-level feedback by aligning retrieval and reasoning with evolving user goals. ChatR1 demonstrates strong performance on both 3B and 7B model backbones, outperforming competitive models on five CQA datasets, measured by different metrics (F1, BERTScore, and LLM-as-judge). We include a diverse set of CQA datasets to cover topic shifts, evolving intents, mixed-initiative dialogues, and multi-document grounding, testing ChatR1's performance from various aspects. Ablation studies confirm the effectiveness of the intent-aware reward. Our analyses further reveal diverse reasoning trajectories and effective use of the search tool. ChatR1 also generalizes robustly across domains, demonstrating that RL-based reasoning enables more flexible and context-aware behavior than static CQA pipelines.

 ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering

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.

Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics

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/}

Downloads

Next from ACL 2026

Aligning Language Models with Real-time Knowledge Editing

Similar lecture

The Unreasonable Effectiveness of Easy Training Data for Hard Tasks