Austria

With the rising need for speech-based interaction models, end-to-end Spoken Language Models (SLMs) have emerged as a promising solution. While these models require comprehensive world knowledge for meaningful and reliable human interactions, existing question-answering (QA) benchmarks fall short in evaluating SLMs&#39; knowledge understanding due to their inability to support end-to-end speech evaluation and account for varied input audio conditions. To address these limitations, we present VoxEval, a novel SpeechQA benchmark that assesses SLMs&#39; knowledge understanding through pure speech interactions. Our benchmark uniquely maintains speech format for both inputs and outputs, evaluates model robustness across diverse input audio conditions, and pioneers the assessment of complex tasks like mathematical reasoning in spoken format. Through systematic evaluation, we demonstrate that current SLMs exhibit poor performance on VoxEval, show sensitivity to varying audio conditions, and possess limited reasoning capabilities, highlighting critical areas for future development. VoxEval dataset is available at: https://github.com/dreamtheater123/VoxEval

ACL 2025

VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models

knowledge understanding

speech language model

benchmark

### 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)

With the rising need for speech-based interaction models, end-to-end Spoken Language Models (SLMs) have emerged as a promising solution. While these models require comprehensive world knowledge for meaningful and reliable human interactions, existing question-answering (QA) benchmarks fall short in evaluating SLMs' knowledge understanding due to their inability to support end-to-end speech evaluation and account for varied input audio conditions. To address these limitations, we present VoxEval, a novel SpeechQA benchmark that assesses SLMs' knowledge understanding through pure speech interactions. Our benchmark uniquely maintains speech format for both inputs and outputs, evaluates model robustness across diverse input audio conditions, and pioneers the assessment of complex tasks like mathematical reasoning in spoken format. Through systematic evaluation, we demonstrate that current SLMs exhibit poor performance on VoxEval, show sensitivity to varying audio conditions, and possess limited reasoning capabilities, highlighting critical areas for future development. VoxEval dataset is available at: https://github.com/dreamtheater123/VoxEval

poster

Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations. Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still face several limitations: additional deployment costs of separate retrievers, redundant input tokens from retrieved text chunks, and the lack of joint optimization of retrieval and generation. To address these issues, we propose \textbf{RetroLLM}, a unified framework that integrates retrieval and generation into a single, auto-regressive process, enabling LLMs to directly generate fine-grained evidence from the corpus with constrained decoding. Moreover, to mitigate false pruning in the process of constrained evidence generation, we introduce (1) hierarchical FM-Index constraints, which generate corpus-constrained clues to identify a subset of relevant documents before evidence generation, reducing irrelevant decoding space; and (2) a forward-looking constrained decoding strategy, which considers the relevance of future sequences to improve evidence accuracy. Extensive experiments on five open-domain QA datasets demonstrate RetroLLM's superior performance across both in-domain and out-of-domain tasks. The code is available at https://anonymous.4open.science/r/RetroLLM-D95A.

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation

Large language models enhance collaborative task execution in multi-agent systems. Current studies break complex task into manageable tasks, but agents lack understanding of the overall task and how others approach their tasks, hindering synergy and integration.

We propose a method called knowledgeable {\bf {\em A}}gents to design and perform {\bf {\em C}}omplex {\bf {\em T}}asks (ACT), where: (1) Agents independently manage their knowledge and tasks while collaboratively design the complex task into a more comprehensible form. In parallel, each agent also acquires knowledge of others, defined as a structured description of how other agents approach their tasks based on the agent's own task resolution. (2) Each agent updates its knowledge and refines its task through interactions with others. By referencing structured knowledge, they effectively integrate their tasks to collaboratively solve the complex task.

Three evaluations including creative writing and tool utilization, show that ACT accurately outperforms existing methods in solving complex tasks.

ACT: Knowledgeable Agents to Design and Perform Complex Tasks

Question Answering (QA) accounts for a significant portion of LLM usage in the wild''. However, LLMs sometimes produce false or misleading responses, also known as hallucinations''. Therefore, grounding the generated answers in contextually provided information---i.e., providing evidence for the generated text---is paramount for LLMs' trustworthiness. Providing this information is the task of context attribution. In this paper, we systematically study LLM-based approaches for this task, namely we investigate (i) zero-shot inference, (ii) LLM ensembling, and (iii) fine-tuning of small LMs on synthetic data generated by larger LLMs. Our key contribution is SynQA: a novel generative strategy for synthesizing context attribution data. Given selected context sentences, an LLM generates QA pairs that are supported by these sentences. This leverages LLMs’ natural strengths in text generation while ensuring clear attribution paths in the synthetic training data. We show that the attribution data synthesized via SynQA is highly effective for fine-tuning small LMs for context attribution in different QA tasks and domains. Finally, with a user study, we validate the usefulness of small LMs (fine-tuned on synthetic data from SynQA) in context attribution for QA.

On Synthesizing Data for Context Attribution in Question Answering

Automatic movie narration aims to generate video-aligned plot descriptions to assist visually impaired audiences. Unlike standard video captioning, it involves not only describing key visual details but also inferring plots that unfold across multiple movie shots, presenting distinct and complex challenges. To advance this field, we introduce Movie101v2, a large-scale, bilingual dataset with enhanced data quality specifically designed for movie narration. Revisiting the task, we propose breaking down the ultimate goal of automatic movie narration into three progressive stages, offering a clear roadmap with corresponding evaluation metrics. Based on our new benchmark, we baseline a range of large vision-language models and conduct an in-depth analysis of the challenges in movie narration generation. Our findings highlight that achieving applicable movie narration generation is a fascinating goal that requires significant research.

Movie101v2: Improved Movie Narration Benchmark

The importance of benchmarks for assessing the values of language models has been pronounced due to the growing need of more authentic, human-aligned responses. However, existing benchmarks rely on human or machine annotations that are vulnerable to value-related biases. Furthermore, the tested scenarios often diverge from real-world contexts in which models are commonly used to generate text and express values. To address these issues, we propose the Value Portrait benchmark, a reliable framework for evaluating LLMs' value orientations with two key characteristics. First, the benchmark consists of items that capture real-life user-LLM interactions, enhancing the relevance of assessment results to real-world LLM usage. Second, each item is rated by human subjects based on its similarity to their own thoughts, and correlations between these ratings and the subjects' actual value scores are derived. This psychometrically validated approach ensures that items strongly correlated with specific values serve as reliable items for assessing those values. Through evaluating 44 LLMs with our benchmark, we find that these models prioritize Benevolence, Security, and Self-Direction values while placing less emphasis on Tradition, Power, and Achievement values. Also, our analysis reveals biases in how LLMs perceive various demographic groups, deviating from real human data.

Value Portrait: Assessing Language Models’ Values through Psychometrically and Ecologically Valid Items

The knowledge within large language models (LLMs) may become outdated quickly. While in-context editing (ICE) is currently the most effective method for knowledge editing (KE), it is constrained by the black-box modeling of LLMs and thus lacks interpretability. Our work aims to elucidate the superior performance of ICE in KE by analyzing the impacts of in-context new knowledge on token-wise distributions. We observe that despite a significant boost in logits of the new knowledge, the performance of ICE is still hindered by stubborn knowledge. We propose a novel approach termed Decoding by Contrasting Knowledge (DeCK). DeCK derives the distribution of the next token by contrasting the logits obtained from the newly edited knowledge guided by ICE with those from the unedited parametric knowledge. Our experiments demonstrate that DeCK enhances the confidence of LLMs in edited facts. For instance, it improves the performance of LLaMA3-8B-instruct on MQuAKE by up to 219%, demonstrating its capability to strengthen ICE. DeCK can be easily integrated into any ICE method as a decoding component to enhance editing capabilities.

Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts

Large Language Models (LLMs) excel in traditional natural language processing tasks but struggle with problems that require complex domain-specific calculations or simulations. While equipping LLMs with external tools to build LLM-based agents can enhance their capabilities, existing approaches lack the flexibility to address diverse and ever-evolving user queries in open domains. Currently, there is also no existing dataset that evaluates LLMs on open-domain knowledge that requires tools to solve. To this end, we introduce OpenAct benchmark to evaluate the open-domain task-solving capability, which is built on human expert consultation and repositories in GitHub. It comprises 339 questions spanning 7 diverse domains that need to be solved with domain-specific methods. In our experiments, even state-of-the-art LLMs and LLM-based agents demonstrate unsatisfactory success rates, underscoring the need for a novel approach.
Furthermore, we present OpenAgent, a novel LLM-based agent system that can tackle evolving queries in open domains through autonomously integrating specialized tools from GitHub. OpenAgent employs 1) a hierarchical framework where specialized agents handle specific tasks and can assign tasks to inferior agents, 2) a bi-level experience learning mechanism to learn from both humans' and its own experiences to tackle tool flaws. Experiments demonstrate its superior effectiveness and efficiency, which significantly outperforms baselines. Our data and code are open-source at https://github.com/OpenBMB/OpenAct.

Enhancing Large Language Model’s Capabilities in Open Domains via Autonomous Tool Integration from GitHub

Training medical personnel using standardized patients (SPs) remains a complex challenge, requiring extensive domain expertise and role-specific practice. Most research on Large Language Model (LLM)-based simulated patients focuses on improving data retrieval accuracy or adjusting prompts through human feedback. However, this focus has overlooked the critical need for patient agents to learn a standardized presentation pattern that transforms data into human-like patient responses through unsupervised simulations. To address this gap, we propose EvoPatient, a novel simulated patient framework in which a patient agent and doctor agents simulate the diagnostic process through multi-turn dialogues, simultaneously gathering experience to improve the quality of both questions and answers, ultimately enabling human doctor training. Extensive experiments on various cases demonstrate that, by providing only overall SP requirements, our framework improves over existing reasoning methods by more than 10% in requirement alignment and better human preference, while achieving an optimal balance of resource consumption after evolving over 200 cases for 10 hours, with excellent generalizability. Our system will be available at https://github.com/ZJUMAI/EvoPatient

LLMs Can Simulate Standardized Patients via Agent Coevolution

Accurate modeling of subjective phenomena such as emotion expression requires data annotated with authors' intentions. Commonly such data is collected by asking study participants to donate and label genuine content produced in the real world, or create content fitting particu- lar labels during the study. Asking participants to create content is often simpler to implement and presents fewer risks to participant privacy than data donation. However, it is unclear if and how study-created content may differ from genuine content, and how differences may impact models. We collect study-created and genuine multimodal social media posts labeled for emotion and compare them on several dimen- sions, including model performance. We find that compared to genuine posts, study-created posts are longer, rely more on their text and less on their images for emotion expression, and focus more on emotion-prototypical events. The samples of participants willing to donate versus create posts are demographically different. Study-created data is valuable to train models that generalize well to genuine data, but realistic effectiveness estimates require genuine data.

Donate or Create? Comparing Data Collection Strategies for Emotion-labeled Multimodal Social Media Posts

Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks. Despite the better user understanding and human-like responses, their **lack of controllability** remains a key challenge, often leading to unfocused conversations or task failure. To address this, we introduce Standard Operating Procedure (SOP) to regulate dialogue flow. Specifically, we propose **ChatSOP**, a novel SOP-guided Monte Carlo Tree Search (MCTS) planning framework designed to enhance the controllability of LLM-driven dialogue agents. To enable this, we curate a dataset comprising SOP-annotated multi-scenario dialogues, generated using a semi-automated role-playing system with GPT-4o and validated through strict manual quality control. Additionally, we propose a novel method that integrates Chain of Thought reasoning with supervised fine-tuning for SOP prediction and utilizes SOP-guided Monte Carlo Tree Search for optimal action planning during dialogues. Experimental results demonstrate the effectiveness of our method, such as achieving a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also showing notable gains for open-source models. Dataset and codes are publicly available.

Downloads

Next from ACL 2025

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation

Similar lecture

Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback