Austria

With the rapid advancement of Large Language Models (LLMs), significant safety concerns have emerged. Fundamentally, the safety of large language models is closely linked to the accuracy, comprehensiveness, and clarity of their understanding of safety knowledge, particularly in domains such as law, policy and ethics. This factuality ability is crucial in determining whether these models can be deployed and applied safely and compliantly within specific regions. To address these challenges and better evaluate the factuality ability of LLMs to answer short question, we introduce the Chinese SafetyQA benchmark. Chinese SafetyQA has several properties (i.e., Chinese, Diverse, High-quality, Static, Easy-to-evaluate, safety-related, harmless). Based on Chinese SafetyQA, we perform a comprehensive evaluation on the factuality abilities of existing LLMs and analyze how these capabilities relate to LLM abilities, e.g., RAG ability and robustness against attacks.

ACL 2025

Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models

safety

chinese

fairness

### 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)

technical paper

Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data. Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the score between queries and candidates, which is challenged by training cost and inference latency with large-scale data. Inspired by the remarkable performance and efficiency of generative models, we propose a generative cross-modal retrieval framework (CART) based on coarse-to-fine semantic modeling, which assigns identifiers to each candidate and treats the generating identifier as the retrieval target. Specifically, we explore an effective coarse-to-fine scheme, combining K-Means and RQ-VAE to discretize multimodal data into token sequences that support autoregressive generation. Further, considering the lack of explicit interaction between queries and candidates, we propose a feature fusion strategy to align their semantics. Extensive experiments demonstrate the effectiveness of the strategies in the CART, achieving excellent results in both retrieval performance and efficiency.

ACE: A Generative Cross-Modal Retrieval Framework With Coarse-To-Fine Semantic Modeling

The subtlety of emotional expressions makes implicit emotion analysis (IEA) particularly sensitive to user-specific characteristics. Current studies personalize emotion analysis by focusing on the author but neglect the impact of the intended reader on implicit emotional feedback. In this paper, we introduce Personalized IEA (PIEA) and present the RAPPIE model, which addresses subjective variability by incorporating reader feedback. In particular, (1) we create reader agents based on large language models to simulate reader feedback, overcoming the issue of ``spiral of silence effect'' and data incompleteness of real reader reaction. (2) We develop a role-aware multi-view graph learning to model the emotion interactive propagation process in scenarios with sparse reader information. (3) We construct two new PIEA datasets covering English and Chinese social media with detailed user metadata, addressing the text-centric limitation of existing datasets. Extensive experiments show that RAPPIE significantly outperforms state-of-the-art baselines, demonstrating the value of incorporating reader feedback in PIEA.

My Words Imply Your Opinion: Reader Agent-Based Propagation Enhancement for Personalized Implicit Emotion Analysis

The existing research has primarily focused on text and image-based hate speech detection, video-based approaches remain underexplored. In this work, we introduce a novel dataset, ImpliHateVid, specifically curated for implicit hate speech detection in videos. ImpliHateVid consists of 2,009 videos comprising 509 implicit hate videos, 500 explicit hate videos, and 1,000 non-hate videos, making it one of the first large-scale video datasets dedicated to implicit hate detection. We also propose a novel two-stage contrastive learning framework for hate speech detection in videos. In the first stage, we train modality-specific encoders for audio, text, and image using contrastive loss by concatenating features from the three encoders. In the second stage, we train cross-encoders using contrastive learning to refine multimodal representations. Additionally, we incorporate sentiment, emotion, and caption-based features to enhance implicit hate detection. We evaluate our method on two datasets, ImpliHateVid for implicit hate speech detection and another dataset for general hate speech detection in videos, HateMM dataset, demonstrating the effectiveness of the proposed multimodal contrastive learning for hateful content detection in videos and the significance of our dataset.

ImpliHateVid: A Benchmark Dataset and Two-stage Contrastive Learning Framework for Implicit Hate Speech Detection in Videos

Information extraction (IE) from Visually Rich Documents (VRDs) containing layout features along with text is a critical and well-studied task. Specialized non-LLM NLP-based solutions typically involve training models using both textual and geometric information to label sequences/tokens as named entities or answers to specific questions. However, these approaches lack reasoning, are not able to infer values not explicitly present in documents, and do not generalize well to new formats. Generative LLMs-based approaches proposed recently are capable of reasoning, but struggle to comprehend clues from document layout especially in previously unseen document formats, and do not show competitive performance in heterogeneous VRD benchmark datasets. In this paper, we propose BLOCKIE, a novel LLM-based approach that organizes VRDs into localized, reusable semantic textual segments called $\textit{semantic blocks}$, which are processed independently. Through focused and more generalizable reasoning,our approach outperforms the state-of-the-art on public VRD benchmarks by 1-3\% in F1 scores, is resilient to document formats previously not encountered and shows abilities to correctly extract information not explicitly present in documents.

Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual Segments

LLMs demonstrate remarkable utility but remain vulnerable to jailbreak attacks that aim to elicit harmful responses. Existing defenses, including post-training alignment and prompt engineering, rely on training on safety-annotated datasets and safe prompt templates, struggling with adaptability to out-of-distribution (OOD) attacks. Steering internal representations of LLMs provides real-time adjustments to defend against OOD attacks. However, it struggles with maintaining model utility, since modifying the representation disrupts the forward pass of inference. It barely considers the competitive objectives of helpfulness and harmlessness in LLMs. We argue that adversarial game-based approaches promise a solution for conflicts between the two objectives. In this paper, we propose **A**dversarial **G**ame **D**efense (AGD), an adversarial game-based defense method that dynamically adjusts LLMs' internal representations to achieve a balanced trade-off between helpfulness and harmlessness. AGD first proposes an interquartile range (IQR) method to detect abnormal attention weights and correct the abnormal weights via adversarial training. AGD adopts a bi-level optimization to play a two-player variable-sum game to approach Nash Equilibrium (NE), where the two players adversarially refine head activations for helpfulness and harmlessness respectively. Furthermore, AGD applies an expert model to next-token sampling to generate safer responses. Experiments show that AGD significantly improves LLMs' safety over all baselines.

AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models

Most written natural languages are composed of sequences of words and sentences. Similar to humans, large language models (LLMs) exhibit flexibility in handling textual positions - a phenomenon we term Position Generalization. They can understand texts with position perturbations and generalize to longer texts than those encountered during training with the latest techniques. These phenomena suggest that LLMs handle positions in a tolerant manner, but how LLMs computationally process positional relevance remains largely unexplored. In this work, we show how LLMs enforce certain computational mechanisms to allow for the aforementioned tolerance in position perturbations. Despite the complex design of the self-attention mechanism, in this work, LLMs are revealed to learn a counterintuitive disentanglement of attention logits, where their values show a 0.959 linear correlation with an approximation of the arithmetic sum of positional relevance and semantic importance. Furthermore, we identify a prevalent pattern in intermediate features that enables this effect, suggesting that it is a learned behavior rather than a natural result of the model architecture. Based on these findings, we provide computational explanations and criteria for the aforementioned position flexibilities observed in LLMs.

Computation Mechanism Behind LLM Position Generalization

Large language models (LLMs) have shown remarkable performance in reasoning tasks but face limitations in mathematical and complex logical reasoning. Existing methods to improve LLMs' logical capabilities either involve traceable or verifiable logical sequences that generate more reliable responses by constructing logical structures yet increase computational costs, or introduces rigid logic template rules, reducing flexibility. In this paper, we propose Reversal of Thought (RoT), a plug-and-play and cost-effective reasoning framework designed to enhance the logical reasoning abilities of LLMs during the warm-up phase prior to batch inference. RoT utilizes a Preference-Guided Reverse Reasoning warm-up strategy, which integrates logical symbols for pseudocode planning through meta-cognitive mechanisms and pairwise preference self-evaluation to generate task-specific prompts solely through demonstrations, aligning with LLMs’ cognitive preferences shaped by RLHF. Through reverse reasoning, we utilize a Cognitive Preference Manager to assess knowledge boundaries and further expand LLMs’ reasoning capabilities by aggregating solution logic for known tasks and stylistic templates for unknown tasks. Experiments across various tasks demonstrate that RoT surpasses existing baselines in both reasoning accuracy and efficiency.

Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up

Large Language Models (LLMs) offer a transparent brain with accessible parameters that encode extensive knowledge, which can be analyzed, located and transferred. Consequently, a key research challenge is to transcend traditional knowledge transfer paradigms rooted in symbolic language and achieve genuine Parametric Knowledge Transfer (PKT). Significantly, exploring effective methods for transferring knowledge across LLMs of different scales through parameters presents an intriguing and valuable research direction. In this paper, we first demonstrate $\textbf{Alignment}$ in parametric space is the fundamental prerequisite to achieve successful cross-scale PKT. We redefine the previously explored knowledge transfer as Post-Align PKT (PostPKT), which utilizes extracted parameters for LoRA initialization and requires subsequent fine-tune for alignment. Hence, to reduce cost for further fine-tuning, we introduce a novel Pre-Align PKT (PrePKT) paradigm and propose a solution called $\textbf{LaTen}$ ($\textbf{L}$oc$\textbf{a}$te-$\textbf{T}$h$\textbf{e}$n-Alig$\textbf{n}$) that aligns the parametric spaces of LLMs across scales only using several training steps without following training. Comprehensive experiments on four benchmarks demonstrate that both PostPKT and PrePKT face challenges in achieving consistently stable transfer. Through in-depth analysis, we identify $\textbf{Neural Incompatibility}$ as the ethological and parametric structural differences between LLMs of varying scales, presenting fundamental challenges to achieving effective PKT. These findings provide fresh insights into the parametric architectures of LLMs and highlight promising directions for future research on efficient PKT. Our code is available at https://github.com/Trae1ounG/Neural_Incompatibility.

Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models

Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of tasks in different domains. However, they sometimes generate responses that are logically coherent but factually incorrect or misleading, which is known as LLM hallucinations. Data-driven supervised methods train hallucination detectors by leveraging the internal states of LLMs, but detectors trained on specific domains often struggle to generalize well to other domains. In this paper, we aim to enhance the cross-domain performance of supervised detectors with only in-domain data. We propose a novel framework, prompt-guided internal states for hallucination detection of LLMs, namely PRISM. By utilizing appropriate prompts to guide changes to the structure related to text truthfulness in LLMs' internal states, we make this structure more salient and consistent across texts from different domains. We integrated our framework with existing hallucination detection methods and conducted experiments on datasets from different domains. The experimental results indicate that our framework significantly enhances the cross-domain generalization of existing hallucination detection methods.

Prompt-Guided Internal States for Hallucination Detection of Large Language Models

While Large Language Models (LLMs) support long contexts, they struggle with performance degradation within the context window. Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored. From the decoding perspective, we identify the Posterior Salience Attenuation (PSA) phenomenon, where the salience ratio correlates with long-text performance degradation. Notably, despite the attenuation, gold tokens still occupy high-ranking positions in the decoding space. Motivated by it, we propose the training-free Positional Contrastive Decoding (PCD) that contrasts the logits derived from long-aware attention with those from designed local-aware attention, enabling the model to focus on the gains introduced by large-scale short-to-long training. Through the analysis of long-term decay simulation, we demonstrate that PCD effectively alleviates attention score degradation. Experimental results show that PCD achieves state-of-the-art performance on long-context benchmarks.

Downloads

Next from ACL 2025

ACE: A Generative Cross-Modal Retrieval Framework With Coarse-To-Fine Semantic Modeling

Similar lecture

Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models