Austria

Though current long-context large language models (LLMs) have demonstrated impressive capacities in answering various questions based on extensive text, the lack of citations in their responses makes user verification difficult, leading to concerns about their trustworthiness due to the potential hallucinations. In this work, we aim to enable long-context LLMs to generate responses with fine-grained sentence-level citations on the fly, thereby improving their faithfulness and verifiability. We first introduce LongBench-Cite, an automated benchmark for assessing current LLMs&#39; performance in long-context question answering with citations (LQAC), revealing considerable room for improvement. To this end, we propose CoF (Coarse to Fine), a novel pipeline that utilizes off-the-shelf LLMs to automatically construct long-context QA instances with precise sentence-level citations, and leverage this pipeline to construct LongCite-45k, a large-scale SFT dataset for LQAC. Finally, we train LongCite-8B and LongCite-9B using the constructed dataset, successfully enabling the generation of accurate responses and fine-grained citations in one pass. The evaluation results on LongBench-Cite show that our trained models achieve state-of-the-art citation quality, surpassing advanced proprietary models including GPT-4o. We also discover that SFT with citation information can further improve the correctness of model responses compared to standard long-context SFT.

ACL 2025

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-Context QA

citation generation

long context

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

Though current long-context large language models (LLMs) have demonstrated impressive capacities in answering various questions based on extensive text, the lack of citations in their responses makes user verification difficult, leading to concerns about their trustworthiness due to the potential hallucinations. In this work, we aim to enable long-context LLMs to generate responses with fine-grained sentence-level citations on the fly, thereby improving their faithfulness and verifiability. We first introduce LongBench-Cite, an automated benchmark for assessing current LLMs' performance in long-context question answering with citations (LQAC), revealing considerable room for improvement. To this end, we propose CoF (Coarse to Fine), a novel pipeline that utilizes off-the-shelf LLMs to automatically construct long-context QA instances with precise sentence-level citations, and leverage this pipeline to construct LongCite-45k, a large-scale SFT dataset for LQAC. Finally, we train LongCite-8B and LongCite-9B using the constructed dataset, successfully enabling the generation of accurate responses and fine-grained citations in one pass. The evaluation results on LongBench-Cite show that our trained models achieve state-of-the-art citation quality, surpassing advanced proprietary models including GPT-4o. We also discover that SFT with citation information can further improve the correctness of model responses compared to standard long-context SFT.

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)

Recent advances in Large Language Models (LLMs) have enabled multi-agent systems that simulate real-world interactions with near-human reasoning. While previous studies have extensively examined biases related to protected attributes such as race, the emergence and propagation of biases on socially contentious issues in multi-agent LLM interactions remain underexplored. This study explores how LLM agents shape public opinion through debates on five contentious topics. By simulating over 2,500 debates, we analyze how initially neutral agents, assigned a centrist disposition, adopt specific stances over time. Statistical analyses reveal significant group conformity mirroring human behavior; LLM agents tend to align with numerically dominant groups or more intelligent agents, exerting a greater influence. These findings underscore the crucial role of agent intelligence in shaping discourse and highlight the risks of bias amplification in online interactions. Our results emphasize the need for policy measures that promote diversity and transparency in LLM-generated discussions to mitigate the risks of bias propagation within anonymous online environments.

An Empirical Study of Group Conformity in Multi-Agent Systems

Large language models (LLMs) often exhibit Context Faithfulness Hallucinations, where outputs deviate from retrieved information due to incomplete context integration. Our analysis reveals a strong correlation between token-level uncertainty and hallucinations. We hypothesize that attention mechanisms inherently encode context utilization signals, supported by probing analysis. Based on these insights, we propose **Dynamic Attention-Guided Context Decoding (DAGCD)**, a lightweight framework that leverages attention distributions and uncertainty signals in a single-pass decoding. Experiments on open-book QA datasets demonstrate DAGCD’s effectiveness, yielding significant improvements in faithfulness and robustness while preserving computational efficiency.

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models

Despite remarkable advances in natural language processing, large Language Models (LLMs) are often prone to hallucination during inference due to the limited coverage of their training corpora. Although existing research has attempted to mitigate this limitation through Knowledge Graphs (KGs) enhancement, two core challenges remain: semantic gaps and redundant paths. Although semantic parsing can partially address these issues through precise graph pattern matching, it demonstrates limited generalizability when handling multi-hop reasoning scenarios. To this end, we propose the two-stage FIne-grainEd SemanTic pArsing (FIESTA) framework. In the offline stage, we construct a fine-grained mapping library through phrase-level segmentation. In the online stage, relevant clauses are retrieved and instantiated into local subgraphs, which are then fused into a global information subgraph. Experimental results on two KGQA datasets show the effectiveness ofFIESTA. Notably, it demonstrates a relative performance improvement of 18.5% over the SOTA method on the CWQ dataset.

From Phrases to Subgraphs: Fine-Grained Semantic Parsing with Knowledge Graphs

Integrating knowledge graphs (KGs) to enhance the reasoning capabilities of large language models (LLMs) is an emerging research challenge in claim verification. While KGs provide structured, semantically rich representations well-suited for reasoning, most existing verification methods rely on unstructured text corpora, limiting their ability to effectively leverage KGs. Additionally, despite possessing strong reasoning abilities, modern LLMs struggle with multi-step modular pipelines and reasoning over KGs without adaptation. To address these challenges, we propose ClaimPKG, an end-to-end framework that seamlessly integrates LLM reasoning with structured knowledge from KGs. Specifically, the main idea of ClaimPKG is to employ a lightweight, specialized LLM to represent the input claim as pseudo-subgraphs, guiding a dedicated subgraph retrieval module to identify relevant KG subgraphs. These retrieved subgraphs are then processed by a general-purpose LLM to produce the final verdict and justification. Extensive experiments on the FactKG dataset demonstrate that ClaimPKG achieves state-of-the-art performance, outperforming strong baselines in this research field by 9\%-12\% accuracy points across multiple categories. Furthermore, ClaimPKG exhibits zero-shot generalizability to unstructured datasets such as HoVer and FEVEROUS, effectively combining structured knowledge from KGs with LLM reasoning across various LLM backbones.

ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLM

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their transition to real-world applications reveals a critical limitation: the inability to adapt to individual preferences while maintaining alignment with universal human values. Current alignment techniques adopt a one-size-fits-all approach that fails to accommodate users’ diverse backgrounds and needs. This paper presents the first comprehensive survey of personalized alignment—a paradigm that enables LLMs to adapt their behavior within ethical boundaries based on individual preferences. We propose a unified framework comprising preference memory management, personalized generation, and feedback-based alignment, systematically analyzing implementation approaches and evaluating their effectiveness across various scenarios. By examining current techniques, potential risks, and future challenges, this survey provides a structured foundation for developing more adaptable and ethically-aligned LLMs.

A Survey on Personalized Alignment—The Missing Piece for Large Language Models in Real-World Applications

The alignment of Large Language Models (LLMs) is crucial for ensuring their safety and reliability in practical applications. Direct Preference Optimization (DPO) has emerged as an efficient method that directly optimizes models using preference pairs, significantly reducing resource demands. However, the effectiveness of DPO heavily depends on the data quality, which is frequently compromised by noise. In this work, we propose 𝛾-PO, a dynamic target margin preference optimization algorithm that adjust reward margins at the pairwise level. By introducing instance-specific margin calibration, 𝛾-PO strategically prioritizes high-confidence pairs (those demonstrating higher reward margins) while suppressing potential noise from ambiguous pairs. Moreover, 𝛾-PO is a plug-and-play method, compatible with variants of DPO that rely on reward margin between preference pairs. Across benchmarks such as AlpacaEval2 and Arena-Hard, 𝛾-PO achieves an average 4.4% improvement over other baselines, setting new benchmarks for state-of-the-art performance. Additionally, 𝛾-PO requires minimal code changes and has a negligible impact on training efficiency, making it a robust solution for enhancing LLMs alignment. Our codes are available at https://github.com/sunjie279/gammaPO.

Robust Preference Optimization via Dynamic Target Margins

Multimodal Large Language Models (MLLMs) have revolutionized video understanding, yet are still limited by context length when processing long videos. Recent methods compress videos by leveraging visual redundancy uniformly, yielding promising results. Nevertheless, our quantitative analysis shows that redundancy varies significantly across time and model layers, necessitating a more flexible compression strategy. We propose **FlexReduc**, a training-free method that flexibly reduces visual redundancy by allocating compression ratios among time and layers with theoretical guarantees. Integrated into state-of-the-art MLLMs, FlexReduc improves processing capacity from 256 to 2048 frames while preserving critical information. Experiments on VideoMME, MLVU, LongVideoBench, and LVBench datasets demonstrate that FlexReduc outperforms existing methods by 2.3% and 2.8% for 7B and 72B models, respectively, with even greater improvements of 5.9% and 6.0% on the longest LVBench.

AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding

Natural language interaction has long served as the primary medium through which humans exchange ideas. A key enabler of this communication is the human capacity for Theory of Mind (ToM)—the ability to infer and align with the mental states of others. ToM is usually modeled as components of desires, beliefs, and intentions. Research in linguistics and psychology has shown that people oftentimes reveal their ToM through pragmatic aspects of language. Considering the advancements in natural language generation and perception that Large Language Models (LLMs) have made in recent years, a critical question arises in relation to ToM: can LLM-powered agents develop similar abilities for inferring mental states during natural language communication? This study investigates the extent to which open-source LLaMA models can represent and retain ToM-related constructs, and whether these internal representations contribute to a coherent mental state modeling in a given conversation. Additionally, we explore the potential for manipulating ToM-related information to generate more aligned responses. Empirical evaluations of LLaMA-3 models (3B and 8B) demonstrate that ToM-informed alignment improves response quality, achieving win rates of 63\% and 67\%, respectively. These findings suggest that integrating ToM principles can enhance alignment in LLM-based conversational agents. For further details, refer to the [code repository](https://github.com/cruiseresearchgroup/ToM_and_Alignment).

Beyond Words: Integrating Theory of Mind into Conversational Agents for Human-Like Belief, Desire, and Intention Alignment

Visual commonsense plays a vital role in understanding and reasoning about the visual world. While commonsense knowledge bases like ConceptNet provide structured collections of general facts, they lack visually grounded representations. Scene graph datasets like Visual Genome, though rich in object-level descriptions, primarily focus on directly observable information and lack systematic categorization of commonsense knowledge. We present Visual Commonsense Dataset (VCD), a large-scale dataset containing over 100,000 images and 14 million object-commonsense pairs that bridges this gap. VCD introduces a novel three-level taxonomy for visual commonsense, integrating both Seen (directly observable) and Unseen (inferrable) commonsense across Property, Action, and Space aspects. Each commonsense is represented as a triple where the head entity is grounded to object bounding boxes in images, enabling scene-dependent and object-specific visual commonsense representation. To demonstrate VCD's utility, we develop VCM, a generative model that combines a vision-language model with instruction tuning to discover diverse visual commonsense from images. Extensive evaluations demonstrate both the high quality of VCD and its value as a resource for advancing visually grounded commonsense understanding and reasoning. Our dataset and code will be released on https://github.com/NUSTM/VCD.

VCD: A Dataset for Visual Commonsense Discovery in Images

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning rationales embody various meta-reasoning skills in human cognition such as reflection and decomposition, being difficult to create and acquire. In this work, we introduce Self-Reasoning Language Model (SRLM), where the model itself can synthesize longer CoT data and iteratively improve performance through self-training. By incorporating a few demonstration examples (i.e., 1,000 samples) on how to unfold hidden reasoning chains from existing responses, which act as a reasoning catalyst, we demonstrate that SRLM not only enhances the model’s initial performance but also ensures more stable and consistent improvements in subsequent iterations. Our proposed SRLM achieves an average absolute improvement of more than +2.5 points across five reasoning tasks: MMLU, GSM8K, ARC-C, HellaSwag, and BBH on two backbone models. Moreover, it brings more improvements with more times of sampling during inference, such as absolute +7.89 average improvement with 64 sampling times, revealing the in-depth, diverse and creative reasoning paths in SRLM against the strong baseline .

Downloads

Next from ACL 2025

An Empirical Study of Group Conformity in Multi-Agent Systems

Similar lecture

Enabling Large Language Models to Generate Text with Citations | VIDEO