United States

Machine unlearning has gained increasing attention in recent years, as a promising technique to selectively remove unwanted privacy or copyrighted information from Large Language Models that are trained on a massive scale of human data. However, the emergence of Large Reasoning Models (LRMs), which emphasize long chain-of-thought (CoT) reasoning to address complex questions, presents a dilemma to unlearning: existing methods either struggle to completely eliminate undesired knowledge from the CoT traces or degrade the reasoning performances due to the interference with the reasoning process. To this end, we introduce Counterfactual Unlearning through iterative Preference Optimization (CiPO), a novel framework that redefines unlearning as the targeted intervention of the CoT reasoning in LRMs. More specifically, given a desired unlearning target answer, CiPO instructs LRMs to generate a logically valid counterfactual reasoning trace for preference tuning. As the LRM adjusts to the counterfactual trace, CiPO iteratively updates the preference learning data to increase the discrepancy from the original model. This iterative loop ensures both desirable unlearning and smooth optimization, effectively mitigating the dilemma. Experiments on challenging benchmarks demonstrate that CiPO excels at unlearning, completely removing knowledge from both the intermediate CoT steps and the final answer, while preserving the reasoning abilities of LRMs.

ACL 2026

CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization

## 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.

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.

Harmful content detectors---particularly disinformation classifiers---are predominantly developed and evaluated on Standard American English (\sae{}), leaving their robustness to dialectal variation unexplored. We present \method{}, the first benchmark for evaluating disinformation detection robustness across 50 English dialects spanning U.S., British, African, Caribbean, and Asia-Pacific varieties. Using Multi-VALUE's linguistically-grounded transformations, we introduce \textcolor{blue}{D-CUBE (Dialectal Disinformation Detection Corpus), a core corpus component of 
\method{} comprising} 195K samples derived from established disinformation 
benchmarks. Our evaluation of 16 detection models reveals systematic vulnerabilities: human-written dialectal content degrades detection by 1.4--3.6\% F1, while AI-generated content remains stable. Fine-tuned transformers substantially outperform zero-shot LLMs (96.6\% vs. 78.3\% best-case F1), with some models exhibiting catastrophic failures exceeding 33\% degradation on mixed content. Cross-dialectal transfer analysis across 2,450 dialect pairs shows that multilingual models (mDeBERTa: 97.2\% average F1) generalize effectively, while monolingual models like RoBERTa and XLM-RoBERTa fail on dialectal inputs. These findings demonstrate that current disinformation detectors may systematically disadvantage hundreds of millions of non-\sae{} speakers worldwide. We release the \method{} \textcolor{blue}{benchmark, including the \href{https://anonymous.4open.science/r/dia-harm-61D9/},} and evaluation tools.

DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects

Temporal language does more than place events on a timeline. In news discourse, references to the past, present, and future can function as rhetorical devices that shape interpretation and persuasion. Here, we study \emph{temporal framing}, defined as the persuasive use of time-related language to structure meaning rather than to report chronology. We propose a taxonomy of eight temporal frames grounded in prior work on temporality and framing, and we realize it through expert annotation of a multilingual news corpus. The resulting dataset includes 458 English and German news articles, with over 2K temporally framed sentences and approximately 3K temporal framing annotations identified from a corpus of more than 20K sentences. We analyze frame prevalence, co-occurrence patterns, and lexical cues, and evaluate temporal framing detection using supervised fine-tuning and zero-shot classification. Our experiments show that temporal framing is learnable at the sentence level, with supervised models substantially outperforming zero-shot approaches. We publicly release the corpus to support future research on temporal framing: https://mbzuai-nlp.github.io/temporal-framing/.

Uncovering Temporal Framing in the News

The misuse of large language models (LLMs) requires precise detection of synthetic text. Existing works mainly follow binary or ternary classification settings, which can only distinguish pure human/LLM text or collaborative text at best. This remains insufficient for the nuanced regulation, as the LLM-polished human text and humanized LLM text often trigger different policy consequences. In this paper, we explore fine-grained LLM-generated text detection under a rigorous four-class setting. To handle such complexities, we propose RACE (Rhetorical Analysis for Creator-Editor Modeling), a fine-grained detection method that characterizes the distinct signatures of creator and editor. Specifically, RACE utilizes Rhetorical Structure Theory (RST) to construct a logic graph for the creator's foundation while extracting Elementary Discourse Unit (EDU)-level features for the editor's style. Experiments show that RACE outperforms 12 baselines in identifying fine-grained types with low false alarms, offering a policy-aligned solution for LLM regulation.

Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection

Conversation derailment prediction represents a new paradigm of toxicity detection, where a system predicts from the start of a conversation whether it will derail into toxic exchanges, allowing moderators and users to act preemptively before harm is done. This approach requires a deep understanding of conversation dynamics. Previous work relies on linguistic features rooted in linguistic and social theories. While these features provide signals of conversation dynamics, they are exploratory in nature and potentially reflect a fraction of the overall pragmatic devices shaping the conversation trajectory. To capture the pragmatic dimension of conversations systematically, we start with a framework for annotating pragmatic information of conversations systematically and design summary generation methods to capture conversation trajectory dynamically. We achieve about 10% performance increase over a simple baseline, and 6.47% increase over a strong baseline on a dataset, and a slight performance increase on a benchmark dataset for the task of summarizing conversation dynamics.

A Theoretically Grounded Approach to Summarizing Conversation Dynamics for Forecasting the Derailment of Online Conversations

It is crucial to understand a specific domain by events. Extensive event extraction research has been conducted in many domains such as news, finance, and biology. However, event extraction in scientific domain is still insufficiently supported by comprehensive datasets and tailored methods. Compared with other domains, scientific domain has two characteristics: (1) denser nuggets and events, and (2) more complex information forms. To solve the above problem, considering these two characteristics, we first construct SciEvents, a large-scale multi-event document-level dataset with a schema tailored for scientific domain. It consists of 2,508 documents and 24,381 events under multi-stage manual annotation and quality control. Then, we propose EXCEEDS, an end-to-end scientific event extraction framework by encoding dense nuggets into a grid matrix and simplifying complex event extraction as a nugget-based grid modeling task. Experiments on SciEvents demonstrate state-of-the-art performances of EXCEEDS. Both the SciEvents dataset and the EXCEEDS framework are released publicly to facilitate future research.

EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain

Enhancing the reasoning capabilities of Large Language Models (LLMs) is a key strategy for building agents that ''think then act''. However, recent observations, like OpenAI's o3, suggest a paradox: stronger reasoning often coincides with increased hallucination, yet no prior work has systematically examined whether reasoning enhancement itself causes tool hallucination. We address this gap with the central question: Does strengthening reasoning increase tool hallucination? To answer this, we introduce SimpleToolHalluBench, a diagnostic benchmark measuring tool hallucination in two failure modes: (i) no tool available, and (ii) only distractor tools available. Through controlled experiments, we establish three key findings. First, we demonstrate a causal relationship: progressively enhancing reasoning through RL increases tool hallucination proportionally with task performance gains. Second, this effect transcends overfitting—training on non-tool tasks (e.g., mathematics) still amplifies subsequent tool hallucination. Third, the effect is method-agnostic, appearing when reasoning is instilled via supervised fine-tuning and when it is merely elicited at inference by switching from direct answers to step-by-step thinking. We also evaluate mitigation strategies including Prompt Engineering and Direct Preference Optimization (DPO), revealing a fundamental reliability–capability trade-off: reducing hallucination consistently degrades utility. Mechanistically, Reasoning RL disproportionately collapses tool-reliability–related representations, and hallucinations surface as amplified divergences concentrated in late-layer residual streams. These findings reveal that current reasoning enhancement methods inherently amplify tool hallucination, highlighting the need for new training objectives that jointly optimize for capability and reliability. Our implementation is provided at https://github.com/albert-y1n/Reasoning_Trap.

The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination

The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decision-making under uncertainty remains limited. We initiate a comparative study of LLM risky choices along two dimensions: (1) prospect representation (explicit vs. experience-based) and (2) decision rationale (explanation). Our study, which involves 20 frontier and open LLMs, is complemented by a matched human subjects experiment, which provides one reference point, while an expected payoff maximizing rational agent model provides another. We find that LLMs cluster into two categories: reasoning models (RMs) and conversational models (CMs). RMs tend towards rational behavior, are insensitive to the order of prospects, gain/loss framing, and explanations, and behave similarly whether prospects are explicit or presented via experience history. CMs are significantly less rational, slightly more human-like, sensitive to prospect ordering, framing, and explanation, and exhibit a large description-history gap. Paired comparisons of open LLMs suggest that a key factor differentiating RMs and CMs is training for mathematical reasoning.

Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

Search-augmented LLM agents can produce deep research reports (DRRs), but verifying claim-level factuality remains challenging. Existing fact-checkers usually target general-domain atomic claims, and there is no benchmark to test whether such verifiers transfer to DRRs.
Yet building such a benchmark for DRR fact-checkers is itself difficult because it requires expert judgments over cognitively demanding, domain-specific claims.
In a controlled study with PhD-level specialists, unassisted experts achieve only 60.8\% accuracy on hidden known-answer claims. We therefore propose evolving benchmarking via **Audit-then-Score** (**AtS**), in which labels and rationales remain revisable: when a verifier disagrees with the current benchmark, it submits evidence; an auditor adjudicates the dispute; and accepted revisions update the benchmark before scoring. After three additional **AtS** rounds, expert accuracy rises to 90.9\%, showing that experts are better auditors than one-shot labelers.
We instantiate **AtS** as **DeepFactBench**, a versioned DRR factuality benchmark with auditable rationales, and introduce **DeepFactEval**, a claim-level verifier.
On the frozen **DeepFactBench** release, **DeepFactEval** achieves 83.4\% accuracy, outperforming the best prior deep-research and traditional fact-checkers by 14.3 and 24.9 points, respectively, and transferring well to external factuality datasets.

DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality

English financial NLP has progressed rapidly through benchmarks for sentiment, document understanding, and financial question answering, while Arabic financial NLP remains comparatively under-explored despite strong practical demand for trustworthy finance and Islamic-finance assistants. We introduce SAHM, a document-grounded benchmark and instruction-tuning dataset for Arabic financial NLP and Shari’ah-compliant reasoning. SAHM contains 14,380 expert-verified instances spanning seven tasks: AAOIFI standards QA, fatwa-based QA/MCQ, accounting and business exams, financial sentiment analysis, extractive summarization, and event–cause reasoning, curated from authentic regulatory, juristic, and corporate sources. We evaluate 19 strong open and proprietary LLMs using task-specific metrics and rubric-based scoring for open-ended outputs, and find that Arabic fluency does not reliably translate to evidence-grounded financial reasoning: models are substantially stronger on recognition-style tasks than on generation and causal reasoning, with the largest gaps on event–cause reasoning. We release the benchmark, evaluation framework, and an instruction-tuned model to support future research on trustworthy Arabic financial NLP.

SAHM: A Benchmark for Arabic Financial and Shari’ah-Compliant Reasoning

Modern industrial applications increasingly demand language models that act as agents, capable of multi-step reasoning and tool use in real-world settings. These tasks are typically performed under strict cost and latency constraints, making small agentic models highly desirable. In this paper, we introduce the AgenticQwen family of models, trained via multi-round reinforcement learning (RL) on synthetic data and a limited amount of open-source data. Our training framework combines reasoning RL and agentic RL with dual data flywheels that automatically generate increasingly challenging tasks. The reasoning flywheel increases task difficulty by learning from errors, while the agentic flywheel expands linear workflows into multi-branch behavior trees that better reflect the decision complexity of real-world applications. We validate AgenticQwen on public benchmarks and in an industrial agent system. The models achieve strong performance on multiple agentic benchmarks, and in our industrial agent system, close the gap with much larger models on search and data analysis tasks.

Downloads

Next from ACL 2026

DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects

Similar lecture

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills

.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

DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects

Similar lecture

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills

Downloads