United States

Large language models (LLMs), like human language learners, show patterns influenced by their dominant training language. Just as humans display language patterns influenced by their native tongue (semantic accents) when learning new languages, LLMs often default to English-centric responses even when generating in other languages. However, we observe that explicitly providing cultural context in prompts significantly improves the models&#39; ability to generate culturally localized responses. We term this phenomenon the \emph{explicit-implicit localization gap}, indicating that while cultural knowledge exists within LLMs, it may not naturally surface in multilingual interaction without explicitly including cultural context. In this paper, we (1) quantify this gap in multiple LLMs using a new cultural localization benchmark and find large (&gt;10%) gaps in the majority of investigated models. (2) Demonstrate a fundamental trade-off between localization accuracy and output diversity. (3) Through mechanistic interpretability, we identify the underlying localization mechanisms within LLMs and show that these mechanisms are both language and task agnostic, with individual steering vectors effectively generalizing across different languages and culturally-relevant tasks.

ACL 2026

Localized Cultural Knowledge is Conserved and Controllable in Large Language Models

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

NAACL 2025

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Large language models (LLMs), like human language learners, show patterns influenced by their dominant training language. Just as humans display language patterns influenced by their native tongue (semantic accents) when learning new languages, LLMs often default to English-centric responses even when generating in other languages. However, we observe that explicitly providing cultural context in prompts significantly improves the models' ability to generate culturally localized responses. We term this phenomenon the \emph{explicit-implicit localization gap}, indicating that while cultural knowledge exists within LLMs, it may not naturally surface in multilingual interaction without explicitly including cultural context. In this paper, we (1) quantify this gap in multiple LLMs using a new cultural localization benchmark and find large (>10%) gaps in the majority of investigated models. (2) Demonstrate a fundamental trade-off between localization accuracy and output diversity. (3) Through mechanistic interpretability, we identify the underlying localization mechanisms within LLMs and show that these mechanisms are both language and task agnostic, with individual steering vectors effectively generalizing across different languages and culturally-relevant tasks.

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.

Recent efforts on text-to-audio (TTA) generation are starting to explore fine-grained controllability, e.g., precise timing control, with innovations on conditioning techniques or training-free latent manipulations. However, constrained by data scarcity, their generation performance at scale is still limited. In this study, we recast high-controllability TTA generation as a multi-task learning problem, and introduce a progressive diffusion modeling approach, ControlAudio. Our method adeptly fits distributions conditioned on fine-grained information, including text, timing, and phoneme features, through a step-by-step strategy. First, we propose a data construction method spanning both annotation and simulation, augmenting condition information in the sequence of text, timing, and phoneme. Second, at the model training stage, we pretrain a scalable diffusion transformer (DiT) on large-scale text-audio pairs, achieving high-fidelity TTA generation, and then incrementally integrate the timing and phoneme features, expanding controllability. Finally, at the inference stage, we propose progressively guided generation, which sequentially emphasizes more fine-grained information, aligning inherently with the coarse-to-fine sampling nature of DiT. Extensive experiments show that ControlAudio achieves state-of-the-art performance in terms of temporal accuracy and speech clarity, significantly outperforming existing methods on both objective and subjective evaluations. Demo samples are available at: https://control-audio.github.io/Control-Audio.

ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling

Causal tracing systematically intervenes on a large language model's (LLM's) internal representations to uncover and quantify the causal pathways linking specific inputs or computations to specific metrics of interest, quantifying the LLM's behavior. Building on previous single-component or single-layer studies, this paper presents a unified framework for causally tracing multiple components simultaneously. This framework systematically identifies the subsets of components (e.g., attention heads and multi-layer perceptron neurons) most critical to a desired target performance metric (e.g., accuracy and fairness). This is achieved by incorporating flexible interventions applied to a wide range of desired metrics. To address the combinatorial complexity of the multi-component problem, an efficient algorithm is designed that leverages soft interventions and a carefully designed metric transformation, converting the combinatorial search problem into a continuous one that can be solved efficiently under proper constraints, thereby generating proper binary decisions for selecting components. Experimental results demonstrate that the proposed method efficiently identifies subsets of the model's components that have a high impact on the target metric, outperforming existing baseline approaches.

Multi-component Causal Tracing in Large Language Models

Traditional tabular data synthesis methods often overlook the cross-modal heterogeneity of real-world tables, where structured continuous and discrete attributes coexist with unstructured long-text columns. Existing synthesis approaches struggle to simultaneously achieve accurate statistical fidelity for non-textual attributes and consistent semantic constraints between textual and non-textual attributes. In this work, we establish the first benchmark for long-text tabular data synthesis and introduce a novel metric, termed Textual Column Correlation Fidelity (TCCF), to quantify cross-modal semantic alignment. We propose AFT-Tab, an adversarial fine-tuning framework that synergistically trains an LLM-based text generator and a deep-learning-based non-textual generator. Through a dual-feedback mechanism guided by an LLM discriminator, AFT-Tab ensures both precise statistical distributions and rigorous semantic constraints. Experimental results show that AFT-Tab significantly outperforms state-of-the-art baselines in statistical fidelity, TCCF, diversity, and downstream task utility.

AFT-Tab: Adversarial Fine-Tuning for Tabular Data Synthesis with Long Text Columns

For people affected by blindness and low vision (BLV), safe and independent navigation remains a major challenge, impacting over 2.2 billion individuals worldwide. Although multimodal large language models (MLLMs) offer new opportunities for assistive navigation, progress has been limited by the scarcity of accessibility-aware datasets, requiring labor-intensive, expert annotation. To this end, we introduce GuideDog, a novel dataset containing 22K image-description pairs (2K human-verified) capturing real-world pedestrian scenes across 46 countries. Our human-AI pipeline shifts annotation from generation to verification, grounded in established BLV guidance standards from experts and research, improving scalability while maintaining quality. We also present GuideDogQA, an 818-sample benchmark evaluating object recognition and depth perception. Experiments reveal that depth perception and adherence to these standards remain challenging for current MLLMs. Code and dataset will be publicly available.

GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance

Model merging, typically on Instruct and Thinking models, has shown remarkable performance for efficient reasoning. In this paper, we systematically revisit the simplest merging method that interpolates two weights directly. Particularly, we observe that model interpolation follows a three-stage evolutionary paradigm with distinct behaviors on the reasoning trajectory. These dynamics provide a principled guide for navigating the performance-cost trade-off. Empirical results demonstrate that a strategically interpolated model surprisingly surpasses sophisticated model merging baselines on both efficiency and effectiveness. We further validate our findings with extensive ablation studies on model layers, modules, and decoding strategies. Ultimately, this work demystifies model interpolation and offers a practical framework for crafting models with precisely targeted reasoning capabilities.

Revisiting Model Interpolation for Efficient Reasoning

Recent works have analyzed the impact of individual components of neural networks on gendered predictions, often with a focus on mitigating gender bias. However, mechanistic interpretations of gender tend to (i) focus on a very specific gender-related task, such as gendered pronoun prediction, or (ii) fail to distinguish between the production of \textit{factually gendered outputs} (the correct assumption of gender given a word that carries gender as a semantic property) and \textit{gender biased outputs} (based on a stereotype). To address these issues, we curate Gknow, a benchmark to assess gender knowledge and gender bias in language models across different types of gender-related predictions. Gknow allows us to identify and analyze circuits and individual neurons responsible for gendered predictions. We test the impact of neuron ablation on benchmarks for disentangling stereotypical and factual gender (DiFair and the test set of Gknow), as well as StereoSet. Results show that gender bias and factual gender are severely entangled on the level of both circuits and neurons, entailing that ablation is an unreliable debiasing method. Furthermore, we show that benchmarks for evaluating gender bias can hide the decrease in factual gender knowledge that accompanies neuron ablation. We curate Gknow as a contribution to the continuous development of robust gender bias benchmarks.

GKnow: Measuring the Entanglement of Gender Bias and Factual Gender

For Large Language Models (LLMs) to be reliably deployed, models must effectively know when not to answer: abstain. Reasoning models, in particular, have gained attention for impressive performance on complex tasks. However, reasoning models have been shown to have worse abstention abilities. Taking the vulnerabilities of reasoning models into account, we propose our Query Misalignment Framework. Hallucinations resulting in failed abstention can be reinterpreted as LLMs answering the wrong question (rather than answering a question incorrectly). Based on this framework, we develop a new class of state-of-the-art abstention methods called **Trace Inversion**. First, we generate the reasoning trace of a model. Based on only the trace, we then reconstruct the most likely query that the model responded to. Finally, we compare the initial query with the reconstructed query. Low similarity score between the initial query and reconstructed query suggests that the model likely answered the question incorrectly and is flagged to abstain. Extensive experiments demonstrate that **Trace Inversion** effectively boosts abstention performance in four frontier LLMs across nine abstention QA datasets, beating competitive baselines in 33 out of 36 settings. The code is available at this https://anonymous.4open.science/r/trace-inversion-08BB/.

Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs

Conversational agents, such as ChatGPT and Doubao, have become essential daily assistants for billions of users. To further enhance engagement, these systems are evolving from passive responders to proactive companions. However, existing efforts focus on activation within ongoing dialogues, while overlooking a key real-world bottleneck. In the conversation initiation stage, users may have a vague need but no explicit query intent, creating a first-message barrier where the conversation holds before it begins. To overcome this, we introduce Conversation Starter Generation: generating personalized starters to guide users into conversation. However, unlike in-conversation stages where immediate context guides the response, initiation must operate in a cold-start moment without explicit user intent. To pioneer in this direction, we present IceBreaker that frames human ice-breaking as a two-step handshake: (i) evoke resonance via Resonance-Aware Interest Distillation from session summaries to capture trigger interests, and (ii) stimulate interaction via Interaction-Oriented Starter Generation, optimized with personalized preference alignment and a self-reinforced loop to maximize engagement. Online A/B tests on one of the world's largest conversational agent products show that IceBreaker improves user active days by +1.84‰ and click-through rate by +94.25‰, and has been deployed in production.

IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters

Large Language Models (LLMs) have demonstrated strong cross-domain capabilities, yet their competence in specialized professional tasks remains underexamined. Existing legal benchmarks evaluate isolated tasks or exam-style questions, failing to capture the procedural interdependencies and adjudicative rigor inherent in professional practice. To bridge this gap, we construct JurisBench, a vertical, depth-oriented, domain-specific benchmark designed to evaluate LLMs across key stages of Chinese civil litigation. JurisBench introduces a Linear Depth Simulation track that mirrors the cognitive workflow of professional judges through four sequential, dependency-aware phases: Cause of Action prediction, Focus of Disputes identification, Rationale of the Judgment generation, and Result of the Judgment determination. Results reveal an “illusion of competence”: state-of-the-art models exhibit marked performance degradation in end-to-end pipelines due to cascading error propagation. We identify precise statutory grounding as a persistent bottleneck, highlighting a critical gap between fluent linguistic output and judicial reliability. JurisBench shifts evaluation from isolated legal knowledge to workflow-level task execution, providing a diagnostic framework for legal AI and a template for benchmark design in specialized domains.

JurisBench: A Deep Benchmark for Assessing Large Language Models in Professional Legal Practice

Transformer language model (LM) contextualization mechanisms remain poorly understood. Here, we leverage lexical ambiguity, where a single word has multiple meanings, to isolate attention mechanisms that contribute to word sense disambiguation. We take a ``'developmental' approach: first, using publicly available checkpoints for the Pythia models, we identify inflection points in disambiguation performance across each model in the suite; in 14M and 410M specifically, we identify attention heads whose attention to disambiguating words covaries with overall disambiguation performance across development. We then stress-test the robustness of these heads to stimulus perturbations: in 14M, we find limited robustness, but in 410M, we identify multiple heads with surprisingly generalizable behavior, including the part-of-speech of the disambiguating cue. Then, in a causal analysis, we find that ablating the target heads demonstrably impairs disambiguation performance, particularly in 14M. The developmental analyses of 14M are also reproduced across all random seeds of the model. Together, these results suggest: first, that disambiguation benefits from a constellation of mechanisms, some of which (especially in 14M) are highly sensitive to the position and part-of-speech of the disambiguating cue; and second, that larger models (410M) may contain heads with more robust disambiguation behavior. They also join a growing body of work that highlights the value of adopting a developmental perspective when probing LM mechanisms.

Downloads

Next from ACL 2026

ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling

Similar lecture

Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge