United States

The widespread integration of large language models (LLMs) across diverse domains, from entertainment to healthcare and banking, has underscored the pressing need to address the risks associated with artificial intelligence (AI). Indeed, as LLMs have grown in scale, new challenges have emerged, including privacy breaches, dissemination of misinformation, issues related to robustness and alignment, and concerns regarding the societal biases ingrained in these models. In response, there has been a surge in research focused on responsible AI and AI safety. To address these challenges, recent literature has introduced novel techniques for mitigating the risks associated with LLMs and testing the efficacy of safety protocols through red-teaming. Despite these efforts, concerns persist regarding the perpetuation of biases in next-generation LLMs and the lack of robustness in existing safety measures. Additionally, recent studies have highlighted the tendency of safety safeguards to over-fit certain keywords or identity terms, raising questions about their effectiveness in real-world scenarios. In this thesis proposal, we look at common evaluation practices in LLMs safety and their potential pitfalls.

NAACL 2025

Rethinking Safety Evaluation in Large Language Models: A Research Proposal

large language models

fairness

evaluation

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

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

poster

### 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!

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

Large language models (LLMs) like GPT-4 and LLaMA-3 offer transformative potential across industries, e.g., enhancing customer service, revolutionizing medical diagnostics, or identifying crises in news articles. However, deploying LLMs faces challenges such as limited training data, high computational costs, and issues with transparency and explainability. Our research focuses on distilling compact, parameter-efficient tailored language models (TLMs) from LLMs for domain-specific tasks with comparable performance. Current approaches like knowledge distillation, fine-tuning, and model parallelism address computational efficiency but lack hybrid strategies to balance efficiency, adaptability, and accuracy. We present ANON - an adaptive knowledge distillation framework integrating knowledge distillation with adapters to generate computationally efficient TLMs without relying on labeled datasets. ANON uses cross-entropy loss to transfer knowledge from the teacher's outputs and internal representations while employing adaptive prompt engineering and a progressive distillation strategy for phased knowledge transfer. We evaluated ANON's performance in the crisis domain, where accuracy is critical and labeled data is scarce. Experiments showed that ANON outperforms recent approaches of knowledge distillation, both in terms of the resulting TLM performance and in reducing the computational costs for training and maintaining accuracy compared to LLMs for domain-specific applications.

Streamlining LLMs: Adaptive Knowledge Distillation for Tailored Language Models

Prompt optimization is crucial for improving output quality of Large Language Models (LLMs), but many existing methods are inefficient, requiring extensive computation and manual tuning. We propose Momentum-Aided Prompt Optimization (MAPO), which builds on ProTeGi by incorporating positive natural language "gradients" and a momentum-based memory mechanism to refine prompts while avoiding local minima and oscillations. It also employs beam search and an Upper Confidence Bound (UCB) algorithm for balanced candidate expansion and selection. MAPO achieves faster convergence time with fewer API calls and higher performance than ProTeGi, demonstrating it as a robust and scalable solution for automated prompt optimization in LLMs.

Momentum-Aided Natural Language Gradient Descent for Prompt Optimization

Rapid improvements in large language models have unveiled a critical challenge in human-AI interaction: sycophancy. In this context, sycophancy refers to the tendency of models to excessively agree with or flatter users, often at the expense of factual accuracy. While previous studies have primarily analyzed this behavior in single-turn interactions, its persistence and evolution in multi-step conversations remain largely unexplored. We introduce METHODNAME , a benchmark specifically designed to evaluate sycophancy in extended dialogues, where language models must navigate iterative user feedback, challenges, and persuasion. We prompt models to elicit four types of sycophantic biases. We then propose and test sycophancy reduction strategies, evaluating their effectiveness beyond single-step interactions.

TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models

The recent large-scale emergence of LLMs has left an open space for dealing with their consequences, such as plagiarism or the spread of false information on the Internet. Coupling this with the rise of AI detector bypassing tools, reliable machine-generated text detection is in increasingly high demand. We investigate the paraphrasing attack resilience of various machine-generated text detection methods, evaluating three approaches: fine-tuned RoBERTa, Binoculars, and text feature analysis, along with their ensembles using Random Forest classifiers. We discovered that Binoculars-inclusive ensembles yield the strongest results, but they also suffer the most significant losses during attacks. In this paper, we present the dichotomy of performance versus resilience in the world of AI text detection, which complicates the current perception of reliability among state-of-the-art techniques.

Paraphrasing Attack Resilience of Various Machine-Generated Text Detection Methods

In recent years stylometry has been more investigated in many different fields. Hence, in this work, we are going to study detecting, generating, and evaluating the writing styles of different authors. In the first step, the sentences will be extracted from several different books, each belonging to a different author, to create a dataset. Then the selected models will be trained to detect the author of sentences in the dataset. After that generator models will be trained without paired dataset to generate sentences based on the authors' writing styles. Finally, in order to evaluate the performance of generators, the first trained models will be leveraged to evaluate the generated sentences.

Detecting, Generating, and Evaluating in the Writing Style of Different Authors

Data visualization is integral to any Exploratory Data Analysis (EDA) task. However, generating visualization requires expertise, presenting a steep learning curve and a significant cognitive load. Natural Language Interfaces (NLIs) for EDA aim to lower this barrier by allowing users to generate visualizations through natural language queries. However, complexity remains when EDA is performed collaboratively, requiring an environment to support multi-user interaction. In this thesis proposal, we discuss challenges in user-system interaction in a collaborative multi-user setup, such as errors in visualization generation due to misinterpretation of user requests. We hypothesize that a Conversational Assistant (CA) capable of understanding user-initiated clarification requests and generating accurate responses can improve user experience and support collaborative EDA tasks. To this end, we propose to develop such a CA (Figure [tab:system_issues]) and evaluate it through a user study, thus examining its impact on user experience in a collaborative environment for EDA.

Collaborative Data Exploration through Visualization: A Thesis Proposal Analyzing Impact of Conversational Assistants

This paper proposes SkipCLM, a novel method for improving multilingual machine translation in decoder transformers. We augment contrastive learning for cross-lingual alignment with a trainable skip connection to preserve information crucial for accurate target language generation. Experiments with XGLM-564M on the Flores-101 benchmark demonstrate improved performance, particularly for en-de and en-zh direction translation, compared to both direct sequence-to-sequence training and existing contrastive learning methods.

SkipCLM: Enchancing Crosslingual Alignment of Decoder Transformer Models via Contrastive Learning and Skip Connection

The proportion of responses to a question and its options, known as the response distribution, enables detailed analysis of human society. Recent studies highlight the use of Large Language Models (LLMs) for predicting response distributions as a cost-effective survey method. However, the reliability of these predictions remains unclear. LLMs often generate answers by blindly following instructions rather than applying rational reasoning based on pretraining-acquired knowledge. This study investigates whether LLMs can rationally estimate distributions when presented with explanations of ``artificially generated distributions'' that are against commonsense. Specifically, we assess whether LLMs recognize counterintuitive explanations and adjust their predictions or simply follow these inconsistent explanations. Results indicate that smaller or less human-optimized LLMs tend to follow explanations uncritically, while larger or more optimized models are better at resisting counterintuitive explanations by leveraging their pretraining-acquired knowledge. These findings shed light on factors influencing distribution prediction performance in LLMs and are crucial for developing reliable distribution predictions using language models.

Reliability of Distribution Predictions by LLMs: Insights from Counterintuitive Pseudo-Distributions

LLMs have demonstrated remarkable proficiency in understanding tasks but continue to struggle with long-context comprehension, particularly with content located in the middle of extensive inputs. This limitation, known as the Lost-in-the-Middle (LITM) problem, hinders models from fully processing and utilizing information across lengthy contexts. To address this issue, we introduce pause-tuning, a technique that redistributes attention to enhance comprehension of long-context inputs. Our approach involves fine-tuning language models on datasets with artificially inserted pause tokens, which serve to segment the input into smaller, more manageable parts. We evaluate pause-tuning against alternative approaches using the Needle-in-a-Haystack benchmark, where models must retrieve information embedded within contexts of up to 128K tokens. Experimental results demonstrate significant performance gains, with the LLaMA 3.2 3B Instruct model and the LLaMA 3.1 8B Instruct model improving by 10.61% and 3.57% respectively on average, suggesting that pause-tuning successfully enhances attention redistribution and improves long-context retention. The code and data are
available at <https://anonymous.4open.science/r/LITM-PauseTokens-7357>.

Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration

Theory of Mind (ToM), the ability to understand the mental states of oneself and others, remains a challenging area for large language models (LLMs), which often fail to predict human mental states accurately. In this paper, we introduce UniToMBench, a unified benchmark that integrates the strengths of SimToM and TOMBENCH to systematically improve and assess ToM capabilities in LLMs by integrating multi-interaction task designs and evolving story scenarios. Supported by a custom dataset of over 1,000 hand-written scenarios, UniToMBench combines perspective-taking techniques with diverse evaluation metrics to better stimulate social cognition in LLMs. Through evaluation, we observe that while models like GPT-4o and its experimental version show consistently high accuracy in tasks involving emotional and belief-related scenarios, with results usually above 80%, there is significant variability in their performance across knowledge-based tasks. These results highlight both the strengths and limitations of current LLMs in ToM-related tasks, underscoring the value of UniToMBench as a comprehensive tool for future development.

Next from NAACL 2025

Streamlining LLMs: Adaptive Knowledge Distillation for Tailored Language Models

Similar lecture

Thesis Proposal: Rethinking Safety Evaluation in Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES