United States

Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves inference speed and language understanding but also provides extra defense against jailbreak attacks and lowers the risk of hallucinations. In this work, we investigate the efficiency of code tokenization, in particular from the perspective of data source diversity. We demonstrate that code tokenizers are prone to producing unused, and thus under-trained, tokens due to the imbalance in repository and language diversity in the training data, as well as the dominance of source-specific, repetitive tokens that are often unusable in future inference. By modifying the BPE objective and introducing merge skipping, we implement different techniques under the name Source-Attributed BPE (SA-BPE) to regularize BPE training and minimize overfitting, thereby substantially reducing the number of under-trained tokens while maintaining the same inference procedure as with regular BPE. This provides an effective tool suitable for production use.

ACL 2026

From Where Words Come: Efficient Regularization of Code Tokenizers Through Source Attribution

## 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.

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.

We model utterance production as probabilistic cost-sensitive choice over contextual alternatives, using information-theoretic notions of cost. We distinguish between goal-directed alternatives that realise a fixed communicative intent and goal-agnostic alternatives defined only by contextual plausibility, allowing us to derive speaker- and listener-oriented interpretations of different cost measures. We present a procedure to generate both types of alternative sets using language models. Analysing production choices in open-ended dialogue under both deterministic and noisy cost minimisation, we find that surprisal minimisation relative to goal-directed alternatives provides the strongest explanation of production choices. Uniformity-based costs show weaker overall predictive power, but their influence increases markedly when evaluated relative to goal-agnostic alternatives, consistent with listener-oriented accounts. More broadly, our study suggests that alternative-conditioned optimisation with LM-generated alternatives provides a principled framework for studying speaker and listener pressures in naturalistic language production.

Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue

Information extraction (IE) systems rely on structured data for training, but such annotated data is highly imbalanced across languages, with low-resource languages receiving little attention. Label projection techniques aim to bridge this gap by transferring structured annotations from high-resource to low-resource languages. However, existing methods are either inaccurate or too slow for large-scale use. This work aims to address this problem by developing a more effective method that remains sufficiently efficient for large-scale projection. In particular, we propose to synthesize alignment sequence pairs and fine-tune an encoder model with span alignment objective, while controlling data influence during training. Experimental results across 50+ languages show that our framework consistently outperforms previous state-of-the-art methods while maintaining fast inference speed. In addition, we introduce EXP - the first benchmark for explicit evaluation of label projection, thereby reducing confounders and non-determinism in method assessment.

Towards Fast and Accurate Modeling for Cross-Lingual Label Projection

The increasing use of video data in training multimodal large language models (MLLMs) raises significant concerns on privacy leakage and copyright violations, highlighting the need for detecting improperly used training videos through membership inference attacks (MIAs). Most existing video MIA methods assess model memorization of key semantic concepts within a video (e.g., the name of a well-known movie character). However, such concepts usually appear repeatedly throughout the training corpus, and memorization of them does not constitute reliable evidence that a specific video was used during training. Besides, while some methods mitigate this limitation by capturing relationships between frames, they require a model logit-accessible setting and are impractical in realistic black-box scenarios. To address these challenges, we propose a black-box MIA framework, named VideoMIA, that can provide reliable evidence of specific video data usage for training MLLMs. The key of our method is to leverage temporal dependencies across video frames to evaluate the model's memorization of sequential dynamics within the video data, which cannot be inferred solely from general world knowledge or individual image data. The results across ten MLLMs and four benchmarks demonstrate that our method consistently achieves superior performance over all baselines in black-box evaluation settings. Code is available in https://github.com/jinruiwang258/VideoMIA.

Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models

Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing methods for mitigating over-refusal cannot maintain a low refusal ratio for harmless queries while keeping a high refusal ratio for malicious ones. In this paper, we analyze how system prompts with varying safety levels affect LLM refusal behaviors when facing over-refusal queries. A key observation is that, when LLMs suffer from the over-refusal issue, non-refusal tokens remain present in the next-token candidate list, but the model systematically fails to select them, despite the generation of refusal tokens. Based on this observation, we propose a training-free and model-agnostic approach, Adaptive Contrastive Decoding (AdaCD), to mitigate over-refusal while maintaining LLM safety. First, AdaCD compares the output distributions of the LLM with or without an extreme safety system prompt to refine the refusal token distribution. Second, we introduce an adaptive contrastive decoding strategy that dynamically incorporates or removes the refusal token distribution, adaptively boosting the probability of selecting refusal or non-refusal tokens. Experimental results on five benchmark datasets show that, on average, AdaCD reduces the refusal ratio for over-refusal queries by 10.35%, yet still increases the refusal ratio for malicious queries by 0.13%. Code is available at https://shorturl.at/Z31Oe.

Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding

Existing LLM hallucination mitigation methods, including prompt engineering and model optimization, either hardly alter models' internal knowledge or have poor cross-domain generalization. Contrastive decoding mitigates hallucinations by using layer-wise differences in LLMs. However, prior studies only explore transformer-based models (e.g., GPT), ignoring other effective frameworks like mixture-of-experts (MoE) models. Since MoE alters the traditional transformer architecture, we conduct empirical studies to investigate whether similar layer-wise differences exist in MoEs. Our results show that they do not exist in MoE with shared experts; nevertheless, across different MoEs, higher layers exhibit distinct expert activation patterns between factual and non-factual outputs. Building on these, we propose EAACD, an expert-aware adaptive contrast decoding that uses expert differences in MoE's higher layers to mitigate hallucinations on QA tasks. EAACD splits high‑layer experts into a higher-reliability group and several lower-reliability groups based on their confidence and consistency. It contrasts the higher-reliability group's prediction with each lower-reliability group's prediction to calibrate the model's original predictions. To strengthen this contrast, EAACD amplifies hallucinations from lower-reliability experts via attention and masking to provide stronger negative references. EAACD outperforms all baselines on four datasets

Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs’ Hallucinations

Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on external retrieval, which is similarity-based, can introduce noise, and adds latency. We introduce \textbf{SEAM} (\textbf{S}tructured \textbf{E}xperience \textbf{A}dapter \textbf{M}odule), a lightweight, executor-specific plug-in that stores experience in its parameters and generates a structured, instance-tailored experience entry in a single forward pass to guide a frozen LLM executor. SEAM is trained for utility via executor rollouts and GRPO while keeping the executor frozen, and can be further improved with logged-success SFT after deployment. Experiments on mathematical reasoning benchmarks show consistent accuracy gains across executors with low overhead. Extensive ablation and analysis further elucidate the mechanisms underlying SEAM’s effectiveness and robustness.\footnote{We release our code at \url{https://anonymous.4open.science/r/SEAM}.}

Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs

This paper primarily demonstrates a method to quantitatively assess the alignment between multi-step, structured reasoning in large language models and human preferences. We introduce the Alignment Score, a semantic-level metric that compares a model-produced chain of thought traces with a human-preferred reference by constructing semantic-entropy-based matrices over intermediate steps and measuring their divergence. Our analysis shows that Alignment Score tracks task accuracy across models and hop depths, and peaks at 2-hop reasoning. Empirical results further indicate that misalignment at greater reasoning depths is driven mainly by alignment errors such as thematic shift and redundant reasoning. Viewing chain sampling as drawing from a distribution over reasoning paths, we empirically demonstrate a strong and consistent correlation between Alignment Score and accuracy, readability, and coherence, supporting its use as a diagnostic signal. The code is available.

Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models

Membership inference attack (MIA) has emerged as a promising tool for auditing the training data of LLMs, supporting data privacy and copyright protection. 
Most existing MIA methods rely on the assumption that LLMs assign higher confidence scores to training samples than to non-training ones.
However, since LLMs generate text by sampling high-confidence tokens, they naturally produce AI-generated texts (AIGTs) that also satisfy this assumption.
In this work, we empirically confirm that such AIGTs, regardless of whether they are generated by the target LLM, can lead existing MIAs to assign even higher membership likelihoods than those of true training samples, thereby significantly undermining their reliability.
To address this challenge, we propose a robust membership inference framework for reliably identifying training data.
Our method adopts a mixture-of-experts formulation to jointly model interactions across complementary features derived from multiple MIA methods and AIGT detectors, which can remain robust against adversarially generated samples.
Furthermore, by leveraging expert components, our method provides explainable insights into the characteristics of member data.
Experiments on various datasets and LLMs show that adversarial samples substantially degrade the performance of baselines, whereas our method preserves performance close to that of the unattacked setting.
Codes and datasets are released at https://github.com/kong-hyh/MoMIA.

Robust Membership Inference for Large Language Models under Adversarial Generative Corruption

Reward models (RMs) are the surrogate objectives in reinforcement learning from human feedback (RLHF), and their scores directly steer policy optimization. We show that standard RM training is vulnerable in data subsets where response quality depends only weakly on the context: such instances encourage the RM to ignore the context, leading to context neglect and degraded accuracy. To address this failure mode, we propose Distribution-Aware Reward Modeling (DARM), which augments the RM objective with a conditional mutual information regularizer that maximizes context and the predicted reward conditioned on the response. By explicitly preserving the sensitivity of reward signals to the prompting context, DARM reduces over-reliance on response-only features and improves robustness to contextual variation. Extensive experiments across in-distribution and out-of-distribution settings show that DARM trained RMs deliver more accurate and consistent scoring than strong baselines. We further evaluate its downstream impact in RLHF, where DARM produce better aligned policies. We also demonstrate the necessity of each DARM design component and the impact of key parameters on performance through ablation experiments.

DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data

Figurative language recognition poses significant challenges in NLP, particularly when distinguishing between fine-grained rhetorical categories such as metaphor, metonymy, and simile. This paper formulates the problem as a four-way sentence-level classification task and proposes FL-MSCL, a unified framework integrating prompt-based knowledge injection with supervised contrastive learning. Experiments across both unified and single-class benchmarks demonstrate that FL-MSCL achieves competitive performance compared to State-of-the-Art (SOTA) methods, indicating consistent advantages in cross-category generalization and category-specific detection.

Downloads

Next from ACL 2026

Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue

Similar lecture

R-BPE: Improving BPE-Tokenizers with Token Reuse