United States

To improve the performance of sentence pair modeling tasks, we propose an additional pre-training method, also known as transfer fine-tuning, for pre-trained masked language models.
Pre-training for masked language modeling is not necessarily designed to bring semantically similar sentences closer together in the embedding space.
Our proposed method aims to improve the performance of sentence pair modeling by applying contrastive learning to pre-trained masked language models, in which sentence embeddings of paraphrase pairs are made similar to each other.
While natural language inference corpora, which are standard in previous studies on contrastive learning, are not available on a large-scale for non-English languages, our method can construct a training corpus for contrastive learning from a raw corpus and a paraphrase dictionary at a low cost.
Experimental results on four sentence pair modeling tasks revealed the effectiveness of our method in both English and Japanese.

NAACL 2025

Paraphrase-based Contrastive Learning for Sentence Pair Modeling

paraphrase recognition

paraphrasing

embedding

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

ACL-IJCNLP 2021

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

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

This paper examines how well visual language models (VLMs) understand video question answering (VideoQA) tasks and generate responses accordingly. Recently, VLMs based on Large Language Models (LLMs) have shown remarkable performance, but the processes of understanding and reasoning in VLMs remain under-explored. To tackle this challenge, we propose Video Understanding and Response Consistency Assessment, VURCA, a framework that incorporates a fine-grained question generation and answering process to measure how well the responses generated by VLMs align with what the model understands. In addition, we introduces an extended benchmark dataset, FgNExT-QA, which builds upon NExT-QA by incorporating more fine-grained VideoQA tasks. FgNExT-QA is designed to evaluate fine-grained understanding in video question answering. Through experiments, we found that VLMs demonstrate a significant lack of understanding of both videos and questions, despite their strong QA performance.

Do Video Language Models really understand the video contexts?

Artificial intelligence (AI) is transforming healthcare by improving patient care and access, especially in remote and resource-limited areas, but it also introduces risks such as biased recommendations, misdiagnoses, and inequities that disproportionately affect underserved groups. These issues often arise when AI fails to consider diverse patient characteristics and social determinants of health. To address this, we propose a human-AI storytelling framework that uses speculative narratives, similar to Black Mirror, to simulate potential unintended harms in AI-driven healthcare systems before development or deployment in the real world. By crafting realistic user stories, our approach reveals hidden biases, flawed data assumptions, and over-reliance on automation, helping developers, clinicians, and stakeholders identify risks early. These narrative ``stress tests'' improve AI fairness, transparency, and responsiveness to real-world needs, ultimately enhancing AI safety, promoting health equity, and guiding better system design.

Towards Safer AI in Healthcare: Using Storytelling to Educate About Unintended Harms of AI-Powered Tools

Text Style Transfer (TST) is the task of transforming a text to reflect a particular style while preserving its original content. Evaluating TST outputs is a multidimensional challenge, requiring the assessment of style transfer accuracy, content preservation, and naturalness. Using human evaluation is ideal but costly, same as in other NLP tasks; however, automatic metrics for TST have not received as much attention as metrics for, e.g., machine translation or summarization.
In this paper, we examine both set of existing and novel metrics from broader NLP tasks for TST evaluation, focusing on two popular subtasks—sentiment transfer and detoxification—in a multilingual context comprising English, Hindi, and Bengali. By conducting meta-evaluation through correlation with human judgments, we demonstrate the effectiveness of these metrics when used individually and in ensembles. Additionally, we investigate the potential of Large Language Models (LLMs) as tools for TST evaluation.
Our findings highlight that certain advanced NLP metrics and experimental-hybrid-techniques provide better insights than existing TST metrics for delivering more accurate, consistent, and reproducible TST evaluations.

Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?

The rapid spread of misinformation on social media underscores the need for effective tools to analyze public discourse. In this thesis proposal, we focus on the concept of truthfulness stance and propose a truthfulness stance detection framework that leverages large language models (LLMs) with retrieval-augmented generation (RAG) to enhance the contextual understanding of tweets in relation to claims. The framework is evaluated on a newly developed dataset and established benchmark datasets.
Experimental results demonstrate that our approach outperforms state-of-the-art methods, significantly improving the Macro-F1 score. To highlight the practical impact of truthfulness stance detection in mitigating misinformation, we showcase several real-world applications and potential future directions.

Thesis Proposal: Understanding Misinformation on Social Media Through Truthfulness Stance

We introduce CLEAR (Contrasting Textual Feedback with Experts and Amateurs for Reasoning), a novel approach to language model reasoning that leverages the strengths of a larger (expert) model and smaller (amateur) model. The expert and amateur models each provide feedback on a model's initial output and are contrasted with each other into refined feedback. This feedback is subsequently applied to iteratively improve CLEAR's responses. Across several challenging tasks, CLEAR outperforms other state-of-the-art reasoning methods, notably achieving a state-of-the-art score on the GSM8K benchmark (97.2%).

CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning

In multi-turn dialogues, large language models face a critical challenge of ensuring coherence while adapting to user-specific information.. This study introduces the persona knowledge gap, the discrepancy between a model’s internal understanding and the knowledge required for coherent, personalized conversations. While prior research has recognized these gaps, computational methods for their identification and resolution remain underexplored. We propose Conversation Preference Elicitation and Recommendation (CPER), a novel framework that dynamically detects and resolves persona knowledge gaps using intrinsic uncertainty quantification and feedback-driven refinement. CPER consists of three key modules: a Contextual Understanding Module for preference extraction, a Dynamic Feedback Module for measuring uncertainty and refining persona alignment, and a Persona-Driven Response Generation module for adapting responses based on accumulated user context. We evaluate CPER on two real-world datasets: CCPE-M for preferential movie recommendations and ESConv for mental health support. Using A/B testing, human evaluators preferred CPER's responses 42% more often than baseline models in CCPE-M and 27% more often in ESConv. A qualitative human evaluation confirms that CPER's responses are preferred for maintaining contextual relevance and coherence, particularly in longer (12+ turn) conversations.

(CPER) From Guessing to Asking: An Approach to Resolving Persona Knowledge Gap in LLMs during Multi-Turn Conversations

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.

Rethinking Safety Evaluation in Large Language Models: A Research Proposal

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.

Downloads

Next from NAACL 2025

Do Video Language Models really understand the video contexts?

Similar lecture

Improving Paraphrase Detection with the Adversarial Paraphrasing Task

.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 NAACL 2025

Do Video Language Models really understand the video contexts?

Similar lecture

Improving Paraphrase Detection with the Adversarial Paraphrasing Task

Downloads