United States

Truthfulness (adherence to factual accuracy) and utility (satisfying human needs and instructions) are both fundamental aspects of Large Language Models, yet these goals often conflict (e.g., sell a car with known flaws), making it challenging to achieve both in real-world deployments. We propose AI-LieDar, a framework to study how LLM-based agents navigate these scenarios in an multi-turn interactive setting. We design a set of real-world scenarios where language agents are instructed to achieve goals that are in conflict with being truthful during a multi-turn conversation with simulated human agents. To evaluate the truthfulness at large scale, we develop a truthfulness detector inspired by psychological literature to assess the agents&#39; responses. Our experiment demonstrates that all models are truthful less than 50% of the time, although truthfulness and goal achievement (utility) rates vary across models. We further test the steerability of LLMs towards truthfulness, finding that models can be directed to be deceptive, and even truth-steered models still lie. These findings reveal the complex nature of truthfulness in LLMs and underscore the importance of further research to ensure the safe and reliable deployment of LLMs and AI agents.

NAACL 2025

AI-LieDar : Examine the Trade-off Between Utility and Truthfulness in LLM Agents

human-centered nlp

dialogue and interactive systems

language modeling

generation

nlp applications

### 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**. 

ACL 2025

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

Truthfulness (adherence to factual accuracy) and utility (satisfying human needs and instructions) are both fundamental aspects of Large Language Models, yet these goals often conflict (e.g., sell a car with known flaws), making it challenging to achieve both in real-world deployments. We propose AI-LieDar, a framework to study how LLM-based agents navigate these scenarios in an multi-turn interactive setting. We design a set of real-world scenarios where language agents are instructed to achieve goals that are in conflict with being truthful during a multi-turn conversation with simulated human agents. To evaluate the truthfulness at large scale, we develop a truthfulness detector inspired by psychological literature to assess the agents' responses. Our experiment demonstrates that all models are truthful less than 50% of the time, although truthfulness and goal achievement (utility) rates vary across models. We further test the steerability of LLMs towards truthfulness, finding that models can be directed to be deceptive, and even truth-steered models still lie. These findings reveal the complex nature of truthfulness in LLMs and underscore the importance of further research to ensure the safe and reliable deployment of LLMs and AI agents.

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 aims to efficiently enable large language models (LLMs) to use external knowledge and goal guidance in conversational recommender system (CRS) tasks. Advanced LLMs (e.g., ChatGPT) are limited in domain-specific CRS tasks for 1) generating grounded responses with recommendation-oriented knowledge, or 2) proactively leading the conversations through different dialogue goals. In this work, we first analyze those limitations through a comprehensive evaluation, showing the necessity of external knowledge and goal guidance which contribute significantly to the recommendation accuracy and language quality. In light of this finding, we propose a novel ChatCRS framework to decompose the complex CRS task into several sub-tasks through the implementation of 1) a knowledge retrieval agent using a tool-augmented approach to reason over external Knowledge Bases and 2) a goal-planning agent for dialogue goal prediction. Experimental results on two multi-goal CRS datasets reveal that ChatCRS sets new state-of-the-art benchmarks, improving language quality of informativeness by 17% and proactivity by 27%, and achieving a tenfold enhancement in recommendation accuracy.

ChatCRS: Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems

Text-to-image (T2I) generation models have significantly advanced in recent years. However, effective interaction with these models is challenging for average users due to the need for specialized prompt engineering knowledge and the inability to perform multi-turn image generation, hindering a dynamic and iterative creation process. Recent attempts have tried to equip Multi-modal Large Language Models (MLLMs) with T2I models to bring the user’s natural language instructions into reality. Hence, the output modality of MLLMs is extended, and the multi-turn generation quality of T2I models is enhanced thanks to the strong multi-modal comprehension ability of MLLMs. However, many of these works face challenges in identifying correct output modalities and generating coherent images accordingly as the number of output modalities increases and the conversations go deeper. Therefore, we propose DialogGen, an effective pipeline to align off-the-shelf MLLMs and T2I models to build a Multi-modal Interactive Dialogue System (MIDS) for multi-turn Text-to-Image generation. It is composed of drawing prompt alignment, careful training data curation, and error correction. Moreover, as the field of MIDS flourishes, comprehensive benchmarks are urgently needed to evaluate MIDS fairly in terms of output modality correctness and multi-modal output coherence. To address this issue, we introduce the Multi-modal Dialogue Benchmark (DialogBen), a comprehensive bilingual benchmark designed to assess the ability of MLLMs to generate accurate and coherent multi-modal content that supports image editing. It contains two evaluation metrics to measure the model’s ability to switch modalities and the coherence of the output images. Our extensive experiments on DialogBen and user study demonstrate the effectiveness of DialogGen in producing correct output modalities and coherent multi-modal outputs compared with other State-of-the-Art models. We hope that DialogBen can contribute to the community for building more powerful MIDS.

DialogGen: Multi-modal Interactive Dialogue System with Multi-turn Text-Image Generation

Predicting when to initiate speech in real-world environments remains a fundamental challenge for conversational agents. We introduce FRAMEWORKNAME , a novel framework for real-time speech initiation prediction in egocentric streaming video. By modeling the conversation from the speaker’s first-person viewpoint, FRAMEWORKNAME is tailored for human-like interactions in which a conversational agent must continuously observe its environment and dynamically decide when to talk. Our approach bridges the gap between simplified experimental setups and complex natural conversations by integrating four key capabilities: (1) first-person perspective, (2) RGB processing, (3) online processing, and (4) untrimmed video processing. We also present YT-Conversation, a diverse collection of in-the-wild conversational videos from YouTube, as a resource for large-scale pretraining. Experiments on EasyCom and Ego4D demonstrate that FRAMEWORKNAME outperforms random and silence-based baselines in real time. Our results also highlight the importance of multimodal input and context length in effectively deciding when to speak. Code and data are available at website.

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild

Intent prediction in information-seeking dialogs is challenging and requires a substantial amount of data with human-labeled intents for effective model training. While Large Language Models (LLMs) have demonstrated effectiveness in generating synthetic data, existing methods typically rely on human feedback and are tailored to structured, task-oriented intents. In this paper, we leverage LLMs for zero-shot generation of large-scale, open-domain, intent-aware information-seeking dialogs to serve as training data for intent prediction models. We introduce SOLID, a method that generates dialogs turn by turn using novel self-seeding and multi-intent self-instructing strategies. Additionally, we propose SOLID-RL, a finetuned version that generates an entire dialog in one step using data created with SOLID. SOLID and SOLID-RL are each used to generate over 300k intent-aware dialogs, significantly surpassing the size of existing datasets. Experiments show that intent prediction models trained on sampled dialogs generated by SOLID and SOLID-RL outperform those trained solely on human-generated dialogs. Our findings demonstrate the potential of LLMs to expand training datasets, as they provide valuable resources for conversational agents across multiple tasks. Our self-seeding and self-instructing approaches are adaptable to various conversational data types and languages with minimal modifications.

SOLID: Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking Dialogs

Following the advancement of large language models (LLMs), the development of LLM-based autonomous agents has become prevalent. As a result, the need to understand the security vulnerabilities of these agents has become a critical task. We examine how ReAct agents can be exploited using a straightforward yet effective method we refer to as the foot-in-the-door attack. Our experiments show that indirect prompt injection attacks, prompted by harmless and unrelated requests (such as basic calculations) can significantly increase the likelihood of the agent performing subsequent malicious actions. Our results show that once a ReAct agent's thought includes a specific tool or action, the likelihood of executing this tool in the subsequent steps increases significantly, as the agent seldom re-evaluates its actions. Consequently, even random, harmless requests can establish a ‘foot-in-the-door’, allowing an attacker to embed malicious instructions into the agent's thought process, making it more susceptible to harmful directives. To mitigate this vulnerability, we propose implementing a simple reflection mechanism that prompts the agent to reassess the safety of its actions during execution, which can help reduce the success of such attacks.

Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In

We present ACCORD, a framework and benchmark suite for disentangling the commonsense grounding and reasoning abilities of large language models (LLMs) through controlled, multi-hop counterfactuals. ACCORD introduces formal elements to commonsense reasoning to explicitly control and quantify reasoning complexity beyond the typical 1 or 2 hops. Uniquely, ACCORD can automatically generate benchmarks of arbitrary reasoning complexity, so it scales with future LLM improvements. Indeed, our experiments on state-of-the-art LLMs show performance degrading to below random chance with only moderate scaling, leaving substantial headroom for improvement. We release a leaderboard of the benchmark suite tested in this work, as well as code for automatically generating more complex benchmarks.

ACCORD: Closing the Commonsense Measurability Gap

Large Language Models (LLMs) have demonstrated significant performance improvements across various cognitive tasks. An emerging application is using LLMs to enhance retrieval-augmented generation (RAG) capabilities. These systems require LLMs to understand user queries, retrieve relevant information, and synthesize coherent and accurate responses. Given the increasing real-world deployment of such systems, comprehensive evaluation becomes crucial. To this end, we propose FRAMES (Factuality, Retrieval, And reasoning MEasurement Set), a high-quality evaluation dataset designed to test LLMs' ability to provide factual responses, assess retrieval capabilities, and evaluate the reasoning required to generate final answers. While previous work has provided datasets and benchmarks to evaluate these abilities in isolation, FRAMES offers a unified framework that provides a clearer picture of LLM performance in end-to-end RAG scenarios. Our dataset comprises challenging multi-hop questions that require the integration of information from multiple sources. We present baseline results demonstrating that even state-of-the-art LLMs struggle with this task, achieving 0.40 accuracy with no retrieval. The accuracy is significantly improved with our proposed multi-step retrieval pipeline, achieving an accuracy of 0.66 (>50% improvement). We hope our work will help bridge evaluation gaps and assist in developing more robust and capable RAG systems.

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation

Summarization is one of the most common tasks performed by large language models (LLMs), especially in applications like Retrieval-Augmented Generation (RAG). However, existing evaluations of hallucinations in LLM-generated summaries, and evaluations of hallucination detection models both suffer from a lack of diversity and recency in the LLM and LLM families considered. This paper introduces FaithBench, a summarization hallucination benchmark comprising challenging hallucinations made by 10 modern LLMs from 8 different families, with ground truth annotations by human experts. ``Challenging'' here means summaries on which popular, state-of-the-art hallucination detection models, including GPT-4o-as-a-judge, disagreed on. Our results show GPT-4o and GPT-3.5-Turbo produce the least hallucinations. However, most state-of-the-art hallucination detection models have near 50% accuracies on FaithBench, indicating lots of room for future improvement.

FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs

K-nearest neighbor language models (kNN-LMs), which integrate retrieval with next-word prediction, have demonstrated strong performance in language modeling as well as some downstream NLP benchmarks. These results have led researchers to argue that models trained on poor quality or outdated data could perform well by employing a kNN extension that has access to a higher-quality datastore. In this work, we ask whether this improved ability to recall information really translates into downstream abilities. We extensively evaluate kNN-LMs on a diverse set of tasks, ranging from sentiment classification and commonsense reasoning to multi-hop reasoning. Results show that kNN-LMs excel at memory-intensive tasks, where utilizing the patterns in the input is sufficient for determining the output, but struggle with reasoning tasks that require integrating multiple pieces of information to derive new knowledge. We further demonstrate through oracle experiments and qualitative analysis that even with perfect retrieval, kNN-LMs still fail to determine the correct answers, placing an upper bound on their reasoning performance.

Great Memory, Shallow Reasoning: Limits of kNN-LMs

Language model systems are used to process diverse categories of input requests, ranging from improving creative writing to solving programming challenges. It would be useful to know which categories they are good at. However, existing evaluations compare model performance on pre-defined categories, failing to reflect a system's performance on finer-grained or novel ones. We propose to automatically search for finer-grained categories based on inputs where a system performs well or poorly, and describe them in natural language. To search for these categories, we propose a large number of candidate category descriptions, e.g. ``Communication Improvement'', find the subset of inputs that match the category descriptions, and calculate the performance on these categories; then we sort these categories based on their performance, thereby highlighting those that score high or low. As one application, we apply our method to compare LLaMA 3-70B and Claude 3 Opus, which have similar Elo-ratings on Chatbot Arena; our method finds the former is weaker at making text more professional and humorous while better at providing psychological insights, depicting a more nuanced picture of model performance.

Downloads

Next from NAACL 2025

ChatCRS: Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems

Similar lecture

Truth Knows No Language: Evaluating Truthfulness Beyond English