Austria

There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts. However, these expert models are not either explicitly trained to be safe, or experience a loss in their safety abilities in the process, making them capable of generating harmful content. We observe that simple interpolation between the domain and alignment delta parameters leads to safer domain-specific models that preserve their utility. Building on this, we introduce MergeAlign, a simple, efficient, and effective model merging-based alignment method. We apply MergeAlign on Llama3 models that are experts in medicine and finance, obtaining substantial safety alignment improvements with minimal to no degradation on domain-specific benchmarks. We study the impact of model merging through model similarity metrics and contributions of individual models being merged, as well as the applicability of MergeAlign on more general code and math expert models using the Qwen-2.5 series of models. We hope our findings open new research avenues towards efficient development and deployment of safe expert LLMs.

ACL 2025

Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs

domain-expert llms

safety alignment

model merging

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

poster

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s 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.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

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 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Active perception, a crucial human capability, involves setting a goal based on the current understanding of the environment and performing actions to achieve that goal. Despite significant efforts in evaluating Multimodal Large Language Models (MLLMs), active perception has been largely overlooked. To address this gap, we propose a novel benchmark named ActiView to evaluate active perception in MLLMs. We focus on a specialized form of Visual Question Answering (VQA) that eases and quantifies the evaluation yet challenging for existing MLLMs. Meanwhile, intermediate reasoning behaviors of models are also discussed. Given an image, we restrict the perceptual field of a model, requiring it to actively zoom or shift its perceptual field based on reasoning to answer the question successfully. We conduct extensive evaluation over 30 models, including proprietary and open-source models, and observe that restricted perceptual fields play a significant role in enabling active perception. Results reveal a significant gap in the active perception capability of MLLMs, indicating that this area deserves more attention. We hope that ActiView could help develop methods for MLLMs to understand multimodal inputs in more natural and holistic ways.

ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models

This paper investigates synthetic data generation strategies in developing generative retrieval models for domain-specific corpora, thereby addressing the scalability challenges inherent in manually annotating in-domain queries. We study the data strategies for a two-stage training framework: in the first stage, which focuses on learning to decode document identifiers from queries, we investigate LLM-generated queries across multiple granularity (e.g. chunks, sentences) and domain-relevant search constraints that can better capture nuanced relevancy signals. In the second stage, which aims to refine document ranking through preference learning, we explore the strategies for mining hard negatives based on the initial model's predictions. Experiments on public datasets over diverse domains demonstrate the effectiveness of our synthetic data generation and hard negative sampling approach.

On Synthetic Data Strategies for Domain-Specific Generative Retrieval

We introduce Conversational Function-Calling Evaluation Through Turn-Level Interactions (CONFETTI), a conversational benchmark designed to evaluate the function-calling capabilities and response quality of large language models (LLMs). Current benchmarks lack comprehensive assessment of LLMs in complex conversational scenarios. CONFETTI addresses this gap through 109 human-simulated conversations, comprising 313 user turns and covering 86 APIs. These conversations explicitly target various conversational complexities, such as follow-ups, goal correction and switching, ambiguous and implicit goals. We perform off-policy turn-level evaluation using this benchmark targeting function-calling. Our benchmark also incorporates dialog act annotations to assess agent responses. We evaluate a series of state-of-the-art LLMs and analyze their performance with respect to the number of available APIs, conversation lengths, and chained function calling. Our results reveal that while some models are able to handle long conversations, and leverage more than 20+ APIs successfully, other models struggle with longer context or when increasing the number of APIs. We also report that the performance on chained function-calls is severely limited across the models. Overall, the top performing models on
CONFETTI are Nova Pro (40.01%), Claude Sonnet v3.5 (35.46%) and Llama 3.1 405B (33.19%) followed by command-r-plus (31.18%) and Mistral-Large-2407 (30.07%).

CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions

Typically, when evaluating Theory of Mind, we consider the beliefs of others to be binary: held or not held. But what if someone is unsure about their own beliefs? How can we quantify this uncertainty? We propose a new suite of tasks, challenging language models (LMs) to model the uncertainty of participants in a dialogue. We design these tasks around conversation forecasting, where the goal is to predict the probability of an unobserved conversation outcome. Uniquely, we view conversation agents themselves as forecasters, asking an LM to predict the uncertainty of an individual from their language use. We experiment with scaling methods, bagging, and demographic context for this regression task, conducting experiments on three dialogue corpora (social, negotiation, task-oriented) with eight LMs. While LMs can explain up to 7% variance in the uncertainty of others, we highlight the difficulty of the tasks and room for future work, especially in tasks that require explicit shifts in perspective.

Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others from Conversational Cues

Understanding uncertainty in causality is vital in various domains, including core NLP tasks like event causality extraction, commonsense reasoning, and counterfactual text generation. However, existing literature lacks a comprehensive examination of this area. This survey aims to fill this gap by thoroughly reviewing uncertainty in causality. We first introduce a novel trichotomy, categorizing causal uncertainty into aleatoric (inherent randomness in causal data), epistemic (causal model limitations), and ontological (existence of causal links) uncertainty. We then survey methods for quantifying uncertainty in causal analysis and highlight the complementary relationship between causal uncertainty and causal strength. Furthermore, we examine the challenges that large language models (LLMs) face in handling causal uncertainty, such as hallucinations and inconsistencies, and propose key traits for an optimal causal LLM. Our paper reviews current approaches and outlines future research directions, aiming to serve as a practical guide for researchers and practitioners in this emerging field.

Uncertainty in Causality: A New Frontier

Factuality evaluation aims to detect factual errors produced by language models (LMs) and hence guide the development of more factual models. Towards this goal, we train a factuality evaluator, FenCE, that provides LM generators with claim-level factuality feedback. In particular, we train FenCE to (1) generate textual critiques along with scores and (2) make claim-level judgment based on diverse source documents obtained by various tools, via data augmentation on a combination of public judgment datasets. We then present a framework that leverages FenCE to improve the factuality of LM generators by constructing training data. Specifically, we generate a set of candidate responses, ask FenCE to revise and score each response without introducing lesser-known facts, and train the generator by preferring highly scored revised responses. Experiments show that our data augmentation methods improve the evaluator’s accuracy by 2.9% on LLM-AggreFact. With FenCE, we improve Llama2-7B-chat/Llama3-8B-chat’s factuality rate by 16.86%/14.45% on FActScore, outperforming state-of-the-art factuality finetuning methods by 8.83%/6.96%.

Improving Model Factuality with Fine-grained Critique-based Evaluator

Autonomous agents powered by large vision and language models (VLM) have demonstrated significant potential in completing daily computer tasks, such as browsing the web to book travel and operating desktop software, which requires agents to understand these interfaces. Despite such visual inputs becoming more integrated into agentic applications, what types of risks and attacks exist around them still remain unclear. In this work, we demonstrate that VLM agents can be easily attacked by a set of carefully designed adversarial pop-ups, which human users would typically recognize and ignore. This distraction leads agents to click these pop-ups instead of performing their tasks as usual. Integrating these pop-ups into existing agent testing environments like OSWorld and VisualWebArena leads to an attack success rate (the frequency of the agent clicking the pop-ups) of 86% on average and decreases the task success rate by 47%. Basic defense techniques, such as asking the agent to ignore pop-ups or including an advertisement notice, are ineffective against the attack. Code is available at [this link](https://github.com/SALT-NLP/PopupAttack).

Attacking Vision-Language Computer Agents via Pop-ups

Code localization--identifying precisely where in a codebase changes need to be made--is a fundamental yet challenging task in software maintenance. Existing approaches struggle to efficiently navigate complex codebases when identifying relevant code snippets.
The challenge lies in bridging natural language problem descriptions with the target code elements, often requiring reasoning across hierarchical structures and multiple dependencies.
We introduce \textsc{LocAgent}, a framework that addresses code localization through a graph-guided agent.
By parsing codebases into directed heterogeneous graphs, \textsc{LocAgent} creates a lightweight representation that captures code structures and their dependencies, enabling LLM agents to effectively search and locate relevant entities through powerful multi-hop reasoning.
Experimental results on real-world benchmarks demonstrate that our approach significantly enhances accuracy in code localization.
Notably, our method with the fine-tuned \texttt{Qwen-2.5-Coder-Instruct-32B} model achieves comparable results to SOTA proprietary models at greatly reduced cost (approximately 86\% reduction), reaching up to 92.7\% accuracy on file-level localization while improving downstream GitHub issue resolution success rates by 12\% for multiple attempts (Pass@10). Our code is available at \url{https://github.com/gersteinlab/LocAgent}.

LocAgent: Agentic Code Localization with Graph-Based Indexing

Chinese, as a linguistic system rich in depth and complexity, is characterized by distinctive elements such as ancient poetry, proverbs, idioms, and other cultural constructs. However, current Large Language Models (LLMs) face limitations in these specialized domains, highlighting the need for the development of comprehensive datasets that can assess, continuously update, and progressively improve these culturally-grounded linguistic competencies through targeted training optimizations. To address this gap, we introduce CKnowEdit, the first-ever Chinese knowledge editing dataset designed to correct linguistic, factual, and logical errors in LLMs. We collect seven types of knowledge from a wide range of sources, including classical texts, idioms, and content from Baidu Tieba Ruozhiba, taking into account the unique polyphony, antithesis, and logical structures inherent in the Chinese language. By analyzing this dataset, we highlight the challenges current LLMs face in mastering Chinese. Furthermore, our evaluation of state-of-the-art knowledge editing techniques reveals opportunities to advance the correction of Chinese knowledge.

CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs

Traditional supervised fine-tuning (SFT) strategies for sequence-to-sequence tasks often train models to directly generate the target output. Recent work has shown that guiding models with intermediate steps—such as keywords, outlines, or reasoning chains—can significantly improve performance, coherence, and interpretability. However, these methods often depend on predefined intermediate formats and annotated data, limiting their scalability and generalizability. In this work, we introduce a task-agnostic framework that enables models to generate intermediate ``warmup'' sequences. These warmup sequences, serving as an initial state for subsequent generation, are optimized to enhance the probability of generating the target sequence without relying on external supervision or human-designed structures. Drawing inspiration from reinforcement learning principles, our method iteratively refines these intermediate steps to maximize their contribution to the final output, similar to reward-driven optimization in reinforcement learning with human feedback. Experimental results across tasks such as translation, summarization, and multi-choice question answering for logical reasoning show that our approach outperforms traditional SFT methods, and offers a scalable and flexible solution for sequence-to-sequence tasks.

Downloads

Next from ACL 2025

ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models

Similar lecture

Model Merging and Safety Alignment: One Bad Model Spoils the Bunch