United States

Reasoning-enhanced large language models rely on intermediate reasoning signals to solve complex, multi-step tasks, making reasoning behavior a valuable form of intellectual property. Meanwhile, knowledge distillation enables an adversary to replicate this behavior in a realistic black-box setting by repeatedly querying a deployed model on a target domain and training a local student to imitate its outputs, including reasoning traces. Existing LLM watermarks primarily operate on surface text and decoding-time token biases, and thus fail to provide reliable attribution of reasoning behavior once it is transferred through knowledge distillation. ReasMark entangles the watermark with the target-domain input distribution by selecting watermark tokens from high-frequency prompts, so distillation queries naturally activate it. It then embeds the watermark by score-conditioned losses that create a detectable reasoning-length gap for black-box verification. Comprehensive experiments across multiple LLMs, datasets, and distillation settings demonstrate that ReasMark consistently outperforms existing baselines while preserving task utility.

ACL 2026

ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s 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.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

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 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

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.

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.

Measuring the quality of public deliberation requires evaluating not only civility or argument structure, but also the informational progress of a conversation. We introduce a framework for Conversational Information Gain (CIG) that evaluates each utterance in terms of how it advances collective understanding of the target topic. To operationalize CIG, we model an evolving semantic memory of the discussion: the system extracts atomic claims from utterances and incrementally consolidates them into a structured memory state. Using this memory, we score each utterance along three interpretable dimensions: Novelty, Relevance, and Implication Scope. We annotate 80 segments from two moderated deliberative settings (TV debates and community discussions) with these dimensions and show that memory-derived dynamics (e.g., the number of claim updates) correlate more strongly with human-perceived CIG than traditional heuristics such as utterance length or TF--IDF. We develop effective LLM-based CIG predictors paving the way for information-focused conversation quality analysis in dialogues and deliberative success.

CIG: Measuring Conversational Information Gain in Deliberative Dialogues with Semantic Memory Dynamics

Recovering business requirements from
COBOL and PL/I portfolios is difficult because
logic is scattered across interdependent
programs and data definitions, and existing
analyses seldom yield stakeholder-facing
artifacts. We introduce an LLM-augmented
reverse-engineering pipeline that couples
grammar-based parsing and control-flow
and data-flow analysis with a large language
model to translate an enriched intermediate
representation into structured specifications.
The pipeline produces business requirements
documents, explicit rule catalogues, end-to-end
data lineage, create–read–update–delete
matrices, and field-level source-to-target
mappings, each linked to the supporting code.
In a financial industry setting, containing
3.2 millions of lines of COBOL, the system
achieves 93% agreement with expert-authored
business rules and reduces documentation
effort by approximately 70%, as measured
against manually produced requirement
documents and rule sets. On an additional
internal corpus spanning 3.4M+ lines across
online, batch, and job control workloads, the
approach yields approximately 3.2–3.3× faster
analysis while improving artifact consistency
and traceability.

Leveraging Generative AI for Extracting Business Requirements from Legacy COBOL and PL/I Code

The scalability of high-quality online education is hindered by the high costs and slow cycles of manual content creation.
Despite advancements in video generation, current approaches often fail to ensure pedagogical structure and precise control due to their pixel-level, black-box nature.
In this paper, we propose Generative Teaching, a novel paradigm shifting educators from manual creators to high-level directors who focus on pedagogical intents while agents handle the execution. To realize this vision, we introduce TeachMaster, a multi-agent framework that leverages code as an intermediate semantic medium. Unlike traditional video generation methods, TeachMaster orchestrates a collaborative team of agents, spanning planning, design, and rendering, to automate the production of interpretable, editable, and curriculum-ready educational videos. 
Experiments validate that TeachMaster significantly boosts production efficiency without compromising structural coherence or visual fidelity, slashing production costs to only 0.3% of traditional online course videos and providing a robust solution for scalable education.

TeachMaster: Generative Teaching via Code

Online advertising governance faces significant challenges due to the non-stationary nature of regulatory policies, where emerging mandates (e.g., restrictions on education or aesthetic anxiety) create severe label inconsistencies and reasoning ambiguities in historical datasets. In this paper, we propose ARGUS, a policy-adaptive governance system that enables evolving reinforcement through multi-agent adversarial umpiring. ARGUS addresses the sparsity of new policy data by employing a three-stage framework: (1) Policy Seeding for initial perception; (2) Adversarial Label Rectification, which utilizes a ''Prosecutor-Defender-Umpire'' architecture to resolve conflicts between stale labels and new mandates; and (3) Latent Knowledge Discovery, which employs a tripartite dialectical discussion to unearth sophisticated, ``gray-area'' violations. By leveraging RAG-enhanced policy knowledge and Chain-of-Thought synthesis as dynamic rewards for reinforcement learning, ARGUS synchronizes its reasoning pathways with evolving regulations. Extensive experiments on both industrial and public datasets demonstrate that ARGUS significantly outperforms traditional fine-tuning baselines, achieving superior policy-adaptive learning with minimal gold data.

ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring

Given the ubiquitous nature of Large Language Models (LLMs) and its impressive capabilities, malicious uses of this technology to generate harmful content have been observed. Thus, to mitigate this serious security risk LLMs pose, many researchers have proposed two techniques for detecting synthetic texts generated from LLMs - watermark and automatic detection. The idea with watermarking LLMs involves infusing generated content with algorithmically-identifiable patterns during generation. This makes accurate synthetic text detection achievable with watermark detection. While, for automatic detection, the focus is on using statistical and linguistic cues to reveal authorship of texts as human or LLM. Currently, both types of synthetic text detectors achieve state-of-the-art performance, however, the better detector is still unknown. To ascertain the better detection method, we evaluate each method on their performance on both unperturbed and perturbed (i.e., adversarially manipulated texts) data. We perform a comprehensive study across six different sizes of Qwen2.5 models, six watermark techniques and detectors, two automatic detectors, three authorship obfuscation methods for different levels of syntactic changes, and two datasets of different text lengths. Our results suggest that there is no detector that consistently outperforms on all scenarios. However, we observe that the (1) automatic detectors are better for short synthetic text detection; and (2) watermark detectors perform better defending against the word-level attack implemented.

Synthetic Text Detection in the Age of Large Language Models: Watermark vs. Automatic Detection

Document understanding in real-world applications often requires processing heterogeneous, multi-page document packets containing multiple documents stitched together. Despite recent advances in visual document understanding, the fundamental task of document packet splitting, which involves separating a document packet into individual units, remains largely unaddressed. We present the first comprehensive benchmark dataset, $\textit{DocSplit}$, along with novel evaluation metrics for assessing the document packet splitting capabilities of large language models. $\textit{DocSplit}$ comprises five datasets of varying complexity, covering diverse document types, layouts, and multimodal settings. We formalize the $\textit{DocSplit}$ task, which requires models to identify document boundaries, classify document types, and maintain correct page ordering within a document packet. The benchmark addresses real-world challenges, including out-of-order pages, interleaved documents, and documents lacking clear demarcations. We conduct extensive experiments evaluating multimodal LLMs on our datasets, revealing significant performance gaps in current models' ability to handle complex document splitting tasks. The $\textit{DocSplit}$ benchmark datasets and proposed novel evaluation metrics provide a systematic framework for advancing document understanding capabilities essential for legal, financial, healthcare, and other document-intensive domains. We release the datasets and evaluation code to facilitate future research in document packet processing.

DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting

As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer interaction.
However, the development of such models is constrained by the scarcity of high-quality, multi-speaker conversational data, as existing large-scale resources are predominantly single-speaker or limited in volume.
Addressing the complex dynamics of natural dialogue, such as overlapping and back-channeling remains a challenge, with standard processing pipelines suffering from diarization errors and ASR hallucinations.
To bridge this gap, we present a robust and scalable open-source data processing pipeline designed for full-duplex model.
Our code and project page are publicly available at https://anonymous-2001-j.github.io/sommelier.github.io/.

Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models

Consider an organization whose users send requests in natural language to an AI system that fulfills them by carrying out specific tasks. In this paper, we consider the problem of ensuring such user requests comply with a list of diverse policies determined by the organization with the purpose of guaranteeing the safe and reliable use of the AI system. We propose, to the best of our knowledge, the first benchmark consisting of annotated user requests of diverse compliance with respect to a list of policies. Our benchmark is related to industrial applications in the technology sector. We then use our benchmark to evaluate the performance of various LLM models on policy compliance assessment under different solution methods. We analyze the differences on performance metrics across the models and solution methods, showcasing the challenging nature of our problem.

Policy Compliance of User Requests in Natural Language for AI Systems

Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections. This scale renders manual rectification infeasible, particularly for video advertisements.
However, existing safety-driven methods often suffer from aggressive over-editing, which compromises the advertiser's original semantic intent merely to satisfy compliance.
In this work, we target the rectification of textual violations in video ads, covering both speech transcripts and on-screen text. We propose $\mathcal{R}^3$, a novel framework designed to harmonize compliance with original semantic intent preservation.
Our approach integrates three key innovations: (1) an experience-driven data synthesis framework that bootstraps high-quality supervision via group-**R**elative compliance experience extractor; 
(2) a curriculum **R**einforcement learning strategy with hierarchical rewards designed to enforce compliance while maximizing semantic consistency;
and 
(3) a comprehensive video **R**ectification framework seamlessly integrating text recognition, rewriting, and re-rendering for industrial deployment. Extensive experiments on industrial datasets and online A/B testing demonstrate that $\mathcal{R}^3$ significantly outperforms state-of-the-art baselines, achieving an optimal trade-off between violation rectification and intent preservation.

$\mathcal{R}^3$: Advertisement Compliance $\mathcal{R}$ectification via Group-$\mathcal{R}$elative Experience Extractor and Curriculum $\mathcal{R}$einforcement

The rapid growth of online grocery shopping demands recommendation models that capture cyclical purchasing behavior and diverse user queries. At a large-scale online grocery e-commerce platform, traditional item-level models face scalability and accuracy limitations, motivating category-level recommendation as a more structured and business-aligned solution. We propose GrocLM, a fine-tuned language model for grocery category recommendation in a real-world production setting. Built with a two-stage LoRA-based fine-tuning strategy, GrocLM models repurchasing patterns and implicit category relationships from historical purchase and query data. To ensure discrete and valid outputs, we introduce a trie tree-based constrained decoding mechanism. Extensive experiments on proprietary production data and public datasets demonstrate that GrocLM significantly outperforms strong baselines and surpasses the deployed production model in live testing, improving recommendation precision, category diversity, and scalability.

Downloads

Next from ACL 2026

CIG: Measuring Conversational Information Gain in Deliberative Dialogues with Semantic Memory Dynamics

Similar lecture

Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?