Austria

Retrieval-Augmented Generation (RAG) has emerged as a crucial method for addressing hallucinations in large language models (LLMs). While recent research has extended RAG models to complex noisy scenarios, these explorations often confine themselves to limited noise types and presuppose that noise is inherently detrimental to LLMs, potentially deviating from real-world retrieval environments and restricting practical applicability. In this paper, we define seven distinct noise types from a linguistic perspective and establish a Noise RAG Benchmark (NoiserBench), a comprehensive evaluation framework encompassing multiple datasets and reasoning tasks. Through empirical evaluation of eight representative LLMs with diverse architectures and scales, we reveal that these noises can be further categorized into two practical groups: noise that is beneficial to LLMs (aka beneficial noise) and noise that is harmful to LLMs (aka harmful noise). While harmful noise generally impairs performance, beneficial noise may enhance several aspects of model capabilities and overall performance. Our analysis offers insights for developing robust RAG solutions and mitigating hallucinations across diverse retrieval scenarios. Code is available at https://github.com/jinyangwu/NoiserBench.

ACL 2025

Pandora&#39;s Box or Aladdin&#39;s Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models

retrieval-augmented generation

benchmarking

evaluation

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models

technical paper

### 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)

Clinical trials are vital for evaluation of safety and efficacy of new treatments. However, clinical trials are resource-intensive, time-consuming and expensive to conduct, where errors in trial design, reduced efficacy, and safety events can result in significant delays, financial losses, and damage to reputation. These risks underline the importance of informed and strategic decisions in trial design to mitigate these risks and improve the chances of a successful trial. Identifying similar historical trials is critical as these trials can provide an important reference for potential pitfalls and challenges including serious adverse events, dosage inaccuracies, recruitment difficulties, patient adherence issues, etc. Addressing these challenges in trial design can lead to development of more effective study protocols with optimized patient safety and trial efficiency. In this paper, we present a novel method to identify similar historical trials by summarizing clinical trial protocols and searching for similar trials based on a query trial's protocol. Our approach significantly outperforms all baselines, achieving up to a 78% improvement in recall@1 and a 53% improvement in precision@1 over the best baseline. We also show that our method outperforms all other baselines in partial trial similarity search and zero-shot patient-trial matching, highlighting its superior utility in these tasks.

SECRET: Semi-supervised Clinical Trial Document Similarity Search

Answering complex, long-context questions remains a major challenge for large language models (LLMs) as it requires effective question clarifications and context retrieval. We propose Agentic Long-Context Understanding (AgenticLU), a framework designed to enhance an LLM’s understanding of such queries by integrating targeted self-clarification with contextual grounding within an agentic workflow. At the core of AgenticLU is Chain-of-Clarifications (CoC), where models refine their understanding through self-generated clarification questions and corresponding contextual groundings. By scaling inference as a tree search where each node represents a CoC step, we achieve 97.8% answer recall on NarrativeQA with a search depth of up to three and a branching factor of eight. To amortize the high cost of this search process to training, we leverage the preference pairs for each step obtained by the CoC workflow and perform two-stage model finetuning: (1) supervised finetuning to learn effective decomposition strategies, and (2) direct preference optimization to enhance reasoning quality. This enables AgenticLU models to generate clarifications and retrieve relevant context effectively and efficiently in a single inference pass. Extensive experiments across seven long-context tasks demonstrate that AgenticLU significantly outperforms state-of-the-art prompting methods and specialized long-context LLMs, achieving robust multi-hop reasoning while sustaining consistent performance as context length grows.

Self-Taught Agentic Long Context Understanding

Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks. In this paper, we comprehensively study its key designs to balance the new abilities while retaining the original abilities, and present an effective CPT method that can greatly improve the Chinese language ability and scientific reasoning ability of LLMs. To achieve it, we design specific data mixture and curriculum strategies based on existing datasets and synthetic high-quality data. Concretely, we synthesize multidisciplinary scientific QA pairs based on related web pages to guarantee the data quality, and also devise the performance tracking and data mixture adjustment strategy to ensure the training stability. For the detailed designs, we conduct preliminary studies on a relatively small model, and summarize the findings to help optimize our CPT method. Extensive experiments on a number of evaluation benchmarks show that our approach can largely improve the performance of Llama-3 (8B), including both the general abilities (+8.81 on C-Eval and +6.31 on CMMLU) and the scientific reasoning abilities (+12.00 on MATH and +4.13 on SciEval). Our model, data, and codes are available at https://github.com/RUC-GSAI/Llama-3-SynE.

Towards Effective and Efficient Continual Pre-training of Large Language Models

Diet plays a critical role in human health, yet tailoring dietary reasoning to individual health conditions remains a major challenge. Nutrition Question Answering (QA) has emerged as a popular method for addressing this problem. However, current research faces two critical limitations. On one hand, the absence of datasets involving user-specific medical information severely limits \textit{personalization}. This challenge is further compounded by the wide variability in individual health needs. On the other hand, while large language models (LLMs), a popular solution for this task, demonstrate strong reasoning abilities, they struggle with the domain-specific complexities of personalized healthy dietary reasoning, and existing benchmarks fail to capture these challenges. To address these gaps, we introduce the Nutritional Graph Question Answering (NGQA) benchmark, the first graph question answering dataset designed for personalized nutritional health reasoning. NGQA leverages data from the National Health and Nutrition Examination Survey (NHANES) and the Food and Nutrient Database for Dietary Studies (FNDDS) to evaluate whether a food is healthy for a specific user, supported by explanations of the key contributing nutrients. The benchmark incorporates three question complexity settings and evaluates reasoning across three downstream tasks. Extensive experiments with LLM backbones and baseline models demonstrate that the NGQA benchmark effectively challenges existing models. In sum, NGQA addresses a critical real-world problem while advancing GraphQA research with a novel domain-specific benchmark. Our codebase and dataset are available here.

NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning

Topic modeling plays a vital role in uncovering hidden semantic structures within text corpora, but existing models struggle in low-resource settings where limited target-domain data leads to unstable and incoherent topic inference. We address this challenge by formally introducing domain adaptation for low-resource topic modeling, where a high-resource source domain informs a low-resource target domain without overwhelming it with irrelevant content. We establish a finite-sample generalization bound showing that effective knowledge transfer depends on robust performance in both domains, minimizing latent-space discrepancy, and preventing overfitting to the data. Guided by these insights, we propose DALTA (Domain-Aligned Latent Topic Adaptation), a new framework that employs a shared encoder for domain-invariant features, specialized decoders for domain-specific nuances, and adversarial alignment to selectively transfer relevant information. Experiments on diverse low-resource datasets demonstrate that DALTA consistently outperforms state-of-the-art methods in terms of topic coherence, stability, and transferability.

Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling

Large language models (LLMs) integrated into multi-step agent systems enable complex decision-making processes across various applications. However, their outputs often lack reliability, making uncertainty estimation crucial. Existing uncertainty estimation methods primarily focus on final-step outputs, which fail to account for cumulative uncertainty over the multi-step decision-making process and the dynamic interactions between agents and their environments. To address these limitations, we propose SAUP (Situation Awareness Uncertainty Propagation), a novel framework that propagates uncertainty through each step of an LLM-based agent's reasoning process. SAUP incorporates situational awareness by assigning situational weights to each step's uncertainty during the propagation. Our method, compatible with various one-step uncertainty estimation techniques, provides a comprehensive and accurate uncertainty measure. Extensive experiments on benchmark datasets demonstrate that SAUP significantly outperforms existing state-of-the-art methods, achieving up to 20% improvement in AUROC.

Uncertainty Propagation on LLM Agent

Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily focus on classifying entire documents as watermarked or not, they often neglect the common scenario of identifying individual watermark segments within longer, mixed-source documents. Drawing inspiration from plagiarism detection systems, we propose two novel methods for partial watermark detection. First, we develop a geometry cover detection framework aimed at determining whether there is a watermark segment in long text. Second, we introduce an adaptive online learning algorithm to pinpoint the precise location of watermark segments within the text. Evaluated on three popular watermarking techniques (KGW-Watermark, Unigram-Watermark, and Gumbel-Watermark), our approach achieves high accuracy, significantly outperforming baseline methods. Moreover, our framework is adaptable to other watermarking techniques, offering new insights for precise watermark detection. Our code is publicly available at \url{https://github.com/XuandongZhao/llm-watermark-location}.

Efficiently Identifying Watermarked Segments in Mixed-Source Texts

Detecting text generated by Large Language Models (LLMs) is crucial, yet current detectors often struggle to generalize in open-world settings. We introduce Learning2Rewrite, a novel framework to detect LLM-generated text with exceptional generalization to unseen domains. Capitalized on the finding that LLMs inherently modify LLM-generated content less than human-written text when rewriting, we train an LLM to amplify this disparity, yielding a more distinguishable and generalizable edit distance across diverse text distributions. Extensive experiments on data from 21 independent domains and four major LLMs (GPT-3.5, GPT-4, Gemini, and Llama-3) demonstrate that our detector outperforms state-of-the-art detection methods by up to 23.04\% in AUROC for in-distribution tests, 35.10\% for out-of-distribution tests, and 48.66\% under adversarial attacks. Our unique training objective ensures better generalizability compared to directly training for classification, even when leveraging the same amount of tunable parameters. Our findings suggest that reinforcing LLMs’ inherent rewriting tendencies offers a robust and scalable solution for detecting LLM-generated text.

Learning to Rewrite: Generalized LLM-Generated Text Detection

Creating lyrics and melodies for the vocal track in a symbolic format, known as song composition, demands expert musical knowledge of melody, an advanced understanding of lyrics, and precise alignment between them. Despite achievements in sub-tasks such as lyric generation, lyric-to-melody, and melody-to-lyric, etc, a unified model for song composition has not yet been achieved. In this paper, we introduce SongComposer, a pioneering step towards a unified song composition model that can readily create symbolic lyrics and melodies following instructions. SongComposer is a music-specialized large language model (LLM) that, for the first time, integrates the capability of simultaneously composing lyrics and melodies into LLMs by leveraging three key innovations: 1) a flexible tuple format for word-level alignment of lyrics and melodies, 2) an extended tokenizer vocabulary for song notes, with scalar initialization based on musical knowledge to capture rhythm, and 3) a multi-stage pipeline that captures musical structure, starting with motif-level melody patterns and progressing to phrase-level structure for improved coherence. Extensive experiments demonstrate that SongComposer outperforms advanced LLMs, including GPT-4, in tasks such as lyric-to-melody generation, melody-to-lyric generation, song continuation, and text-to-song creation. Moreover, we will release SongCompose, a large-scale dataset for training, containing paired lyrics and melodies in Chinese and English.

SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition

We study continued training and supervised fine-tuning (SFT) of a language model (LM) to make effective use of long-context information. We first establish a reliable evaluation protocol to guide model development—instead of perplexity or simple needle-in-a-haystack (NIAH) tests, we use a broad set of long-context downstream tasks, and we evaluate models after SFT as this better reveals long-context abilities. Supported by our robust evaluations, we run thorough experiments to decide the data mix for continued pre-training, the instruction tuning dataset, and many other design choices such as position extrapolation. We find that (1) code repositories and books are excellent sources of long data, but it is crucial to combine them with high-quality short-context data; (2) training with a sequence length beyond the evaluation length boosts long-context performance; (3) for SFT, using only short instruction datasets yields strong performance on long-context tasks. Our final model, ProLong-8B, which is initialized from Llama-3 and trained on 40B tokens, demonstrates state-of-the-art long-context performance among similarly sized models at a length of 128K. ProLong outperforms Llama-3.1-8B-Instruct on the majority of long-context tasks despite using only 5% as many tokens during long-context training. Additionally, ProLong can effectively process up to 512K tokens, one of the longest context windows of publicly available LMs.

Downloads

Next from ACL 2025

SECRET: Semi-supervised Clinical Trial Document Similarity Search

Similar lecture

Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training