Austria

Question Answering (QA) with large language models has shown impressive performance, yet hallucinations still persist, particularly when user queries carry incorrect premises, insufficient context, or linguistic ambiguity. To address this issue, we propose Lightweight Query Checkpoint (LQC), a small classification model that detects verification-required queries before the LLM generates a potentially faulty answer. LQC leverages hidden states extracted from intermediate layers of a smaller-scale, non-instruct-tuned LLM to effectively distinguish queries requiring verification from clear queries. We first systematically define categories of queries that need verification, construct a dataset comprising both defective and clear queries, and train a binary contrastive learning model. Through extensive experiments on various QA datasets, we demonstrate that incorporating LQC into QA pipelines reduces hallucinations while preserving strong answer quality.

ACL 2025

Lightweight Query Checkpoint: Classifying Faulty User Queries to Mitigate Hallucinations in Large Language Model Question Answering

question answering (qa)

query verification

llm reliability

lightweight models

hallucination mitigation

large language models (llms)

contrastive learning

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

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)

In-hospital text data contains valuable clinical information, yet deploying fine-tuned small language models (SLMs) for information extraction remains challenging due to differences in formatting and vocabulary across institutions. Since access to the original in-hospital data (source domain) is often restricted, annotated data from the target hospital (target domain) is crucial for domain adaptation. However, clinical annotation is notoriously expensive and time-consuming, as it demands clinical and linguistic expertise. To address this issue, we leverage large language models (LLMs) to annotate the target domain data for the adaptation. We conduct experiments on four clinical information extraction tasks, including eight target domain data. Experimental results show that LLM-annotated data consistently enhances SLM performance and, with a larger number of annotated data, outperforms manual annotation in three out of four tasks.

Exploring LLM Annotation for Adaptation of Clinical Information Extraction Models under Data-sharing Restrictions

The scarcity of publicly available clinical corpora hinders developing and applying NLP tools in clinical research. While existing work tackles this issue by utilizing generative models to create high-quality synthetic corpora, their methods require learning from the original in-hospital clinical documents, turning them unfeasible in practice. To address this problem, we introduce RecordTwin, a novel synthetic corpus creation method designed to generate synthetic documents from anonymized clinical entities. In this method, we first extract and anonymize entities from in-hospital documents to ensure the information contained in the synthetic corpus is restricted. Then, we use a large language model to fill the context between anonymized entities. To do so, we use a small, privacy-preserving subset of the original documents to mimic their formatting and writing style. This approach only requires anonymized entities and a small subset of original documents in the generation process, making it more feasible in practice. To evaluate the synthetic corpus created with our method, we conduct a proof-of-concept study using a publicly available clinical database. Our results demonstrate that the synthetic corpus has a utility comparable to the original data and a safety advantage over baselines, highlighting the potential of RecordTwin for privacy-preserving synthetic corpus creation.

RecordTwin: Towards Creating Safe Synthetic Clinical Corpora

Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns. Current approaches to address this issue involve costly dataset scrubbing, or model filtering through unlearning and model editing, which can be bypassed through extraction attacks. We propose REVS, a novel non-gradient-based method for unlearning sensitive information from LMs. REVS identifies and modifies a small subset of neurons relevant for constituent tokens which form sensitive information. To adequately evaluate our method on truly sensitive information, we curate three datasets: an email and URL datasets naturally memorized by the models, and a synthetic social security number dataset that we tune the models to memorize. Compared to other methods, REVS demonstrates superior performance in unlearning sensitive information and robustness to extraction attacks, while retaining underlying model integrity.

REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space

Large Language Model (LLM) agents have demonstrated impressive capabilities in handling complex interactive problems. Existing LLM agents mainly generate natural language plans to guide reasoning, which is verbose and inefficient. NL plans are also tailored to specific tasks and restrict agents’ ability to generalize across similar tasks. To this end, we explore pseudocode-style plans (P-code Plan) to capture the structural logic of reasoning. We find that P-code Plan empowers LLM agents with stronger generalization ability and more efficiency. Inspired by this finding, we propose a pseudocode-style ̲Planning ̲Guided ̲Preference ̲Optimization method called PGPO for effective agent learning. With two planning-oriented rewards, PGPO further enhances LLM agents’ ability to generate high-quality P-code Plans and subsequent reasoning. Experiments show that PGPO achieves superior performance on representative agent benchmarks and outperforms the current leading baselines. Analyses reveal the advantage of PGPO in reducing action errors and omissions during reasoning.

PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization

As autonomous agents powered by large language models (LLMs) continue to demonstrate potential across various assistive tasks, ensuring their safe and reliable behavior is crucial for preventing unintended consequences. In this work, we introduce CIP, a novel technique that leverages causal influence diagrams (CIDs) to identify and mitigate risks arising from agent decision-making. CIDs provide a structured representation of cause-and-effect relationships, enabling agents to anticipate harmful outcomes and make safer decisions. Our approach consists of three key steps: (1) initializing a CID based on task specifications to outline the decision-making process, (2) guiding agent interactions with the environment using the CID, and (3) iteratively refining the CID based on observed behaviors and outcomes. Experimental results demonstrate that our method effectively enhances safety in both code execution and mobile device control tasks.

Enhancing LLM Agent Safety via Causal Influence Prompting

Identifying factors that make ad text attractive is essential for advertising success. This study proposes AdParaphrase v2.0, a dataset for ad text paraphrasing, containing human preference data, to enable the analysis of the linguistic factors and to support the development of methods for generating attractive ad texts. Compared with v1.0, this dataset is 20 times larger, comprising 16,460 ad text paraphrase pairs, each annotated with preference data from ten evaluators, thereby enabling a more comprehensive and reliable analysis. Through the experiments, we identified multiple linguistic features of engaging ad texts that were not observed in v1.0 and explored various methods for generating attractive ad texts. Furthermore, our analysis demonstrated the relationships between human preference and ad performance, and highlighted the potential of reference-free metrics based on large language models for evaluating ad text attractiveness.
The dataset is publicly available at: https://github.com/CyberAgentAILab/AdParaphrase-v2.0.

AdParaphrase v2.0: Generating Attractive Ad Texts Using a Preference-Annotated Paraphrase Dataset

Despite possessing impressive skills, Large Language Models (LLMs) often fail unpre-dictably, demonstrating inconsistent success in even basic common sense reasoning tasks. This unpredictability poses a significant challenge to ensuring their safe deployment, as identifying and operating within a reliable “safe zone” is essential for mitigating risks. To address this, we present PredictaBoard, a novel collabo-rative benchmarking framework designed to evaluate the ability of score predictors (referred to as assessors) to anticipate LLM errors on specific task instances (i.e., prompts) from existing datasets. PredictaBoard evaluates pairs of LLMs and assessors by considering the rejection rate at different tolerance errors. As such, PredictaBoard stimulates research into developing better assessors and making LLMs more predictable, not only with a higher average performance. We conduct illustrative experiments using baseline assessors and state-of-the-art LLMs. PredictaBoard highlights the critical need to evaluate predictability alongside performance, paving the way for safer AI systems where errors are not only minimised but also anticipated and effectively mitigated. Code for our bench-mark can be found at https://github. com/Kinds-of-Intelligence-CFI/PredictaBoard

PredictaBoard: Benchmarking LLM Score Predictability

Grammar serves as a cornerstone in programming languages and software engineering, providing frameworks to define the syntactic space and program structure. Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance. However, as language models scale to the billion level or beyond, syntax-level errors become rare, making it unclear whether grammar information still provides performance benefits. To explore this, we develop a series of billion-scale GrammarCoder models, incorporating grammar rules in the code generation process. Experiments on HumanEval (+) and MBPP (+) demonstrate a notable improvement in code generation accuracy. Further analysis shows that grammar-based representations enhance LLMs' ability to discern subtle code differences, reducing semantic errors caused by minor variations. These findings suggest that grammar-based code representations remain valuable even in billion-scale models, not only by maintaining syntax correctness but also by improving semantic differentiation.

Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?

Large Language Models (LLMs) encapsulate a surprising amount of factual world knowledge. 
However, their performance on temporal questions and historical knowledge is limited because they often cannot understand temporal scope and orientation or neglect the temporal aspect altogether.
In this study, we aim to measure precisely how robust LLMs are for question answering based on their ability to process temporal information and perform tasks requiring temporal reasoning and temporal factual knowledge. 
Specifically, we design eight time-sensitive
robustness tests for factual information to check the sensitivity of six popular LLMs in the zero-shot setting.
Overall, we find LLMs lacking temporal robustness, especially to temporal reformulations and the use of different granularities of temporal references. 
We show how a selection of these eight tests can be used automatically to judge a model’s temporal robustness for user questions on the fly. Finally, we apply the findings of this study to improve the temporal QA performance by up to 55\%.

A Study into Investigating Temporal Robustness of LLMs

Recently, LLMs have garnered increasing attention across academic disciplines for their potential as human digital twins, virtual proxies designed to replicate individuals and autonomously perform tasks such as decision-making, problem-solving, and reasoning on their behalf.
However, current evaluations of LLMs primarily emphasize dialogue simulation while overlooking human behavior simulation, which is crucial for digital twins.
To address this gap, we introduce BehaviorChain, the first benchmark for evaluating LLMs' ability to simulate continuous human behavior.
BehaviorChain comprises diverse, high-quality, persona-based behavior chains, totaling 15,846 distinct behaviors across 1,001 unique personas, each with detailed history and profile metadata.
For evaluation, we integrate persona metadata into LLMs and employ them to iteratively infer contextually appropriate behaviors within dynamic scenarios provided by BehaviorChain. Comprehensive evaluation results demonstrated that even state-of-the-art models struggle with accurately simulating continuous human behavior.

Downloads

Next from ACL 2025

Exploring LLM Annotation for Adaptation of Clinical Information Extraction Models under Data-sharing Restrictions

Similar lecture

CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering