Austria

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but often at the cost of reduced output diversity. This trade-off between diversity and alignment quality remains a significant challenge. Drawing inspiration from curiosity-driven exploration in reinforcement learning, we introduce curiosity-driven RLHF (CD-RLHF), a framework that incorporates intrinsic rewards for novel states, alongside traditional sparse extrinsic rewards, to optimize both output diversity and alignment quality. We demonstrate the effectiveness of CD-RLHF through extensive experiments on a range of tasks, including text summarization and instruction following. Our approach achieves significant gains in diversity on multiple diversity-oriented metrics while maintaining alignment with human preferences comparable to standard RLHF. We will make our code publicly available.

ACL 2025

Curiosity-Driven Reinforcement Learning from Human Feedback

curiosity-driven rl

rlhf

large language models

## 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.

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)

Traditional scaling laws in natural language processing suggest that increasing model size and training data enhances performance. However, recent studies reveal deviations, particularly in large language models, where performance improvements decelerate—a phenomenon known as sub-scaling. This paper revisits these scaling laws by examining the impact of data quality and training strategies on model performance. Through extensive empirical analysis of over 400 models, we identify high data density and non-optimal resource allocation as key factors contributing to sub-scaling. High data density leads to diminishing returns due to redundant information, while optimal resource allocation is crucial for sustained performance improvements. We propose a sub-optimal scaling law that better predicts performance in sub-scaling regimes, highlighting the importance of data quality and diversity.

Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies

Event Argument Extraction (EAE) is a daunting information extraction problem --- with significant limitations in few-shot cross-domain (FSCD) settings. A common solution to FSCD modeling is data augmentation. Unfortunately, existing augmentation methods are not well-suited to a variety of real-world EAE contexts, including (i) modeling long documents (documents with over 10 sentences), and (ii) modeling challenging role types (i.e., event roles with little to no training data and semantically outlying roles). We introduce two novel LLM-powered data augmentation methods for generating extractive document-level EAE samples using zero in-domain training data. We validate the generalizability of our approach on four datasets --- showing significant performance increases in low-resource settings. Our highest performing models provide a 13-pt increase in F1 score on zero-shot role extraction in FSCD evaluation.

Document-Level Event-Argument Data Augmentation for Challenging Role Types

Empathetic response generation necessitates the integration of emotional and intentional dynamics to foster meaningful interactions. Existing research either neglects the intricate interplay between emotion and intent, leading to suboptimal controllability of empathy, or resorts to large language models (LLMs), which incur significant computational overhead. In this paper, we introduce ReflectDiffu, a lightweight and comprehensive framework for empathetic response generation. This framework incorporates emotion contagion to augment emotional expressiveness and employs an emotion-reasoning mask to pinpoint critical emotional elements. Additionally, it integrates intent mimicry within reinforcement learning for refinement during diffusion. By harnessing an intent twice reflect mechanism of Exploring-Sampling-Correcting, ReflectDiffu adeptly translates emotional decision-making into precise intent actions, thereby addressing empathetic response misalignments stemming from emotional misrecognition. Through reflection, the framework maps emotional states to intents, markedly enhancing both response empathy and flexibility. Comprehensive experiments reveal that ReflectDiffu outperforms existing models regarding relevance, controllability, and informativeness, achieving state-of-the-art results in both automatic and human evaluations.

ReflectDiffu: Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework

Recent advancements in NLP, largely driven by Large Language Models (LLMs), have significantly improved performance on an array of tasks. However, Dialogue Act (DA) classification remains challenging, particularly in the fine-grained 50-class, multiparty setting. This paper investigates the root causes of LLMs' poor performance in DA classification through a linguistically motivated analysis. We identify three key pre-tasks essential for accurate DA prediction: Turn Management, Communicative Function Identification, and Dialogue Structure Prediction. Our experiments reveal that LLMs struggle with these fundamental tasks, often failing to outperform simple rule-based baselines. Additionally, we establish a strong empirical correlation between errors in these pre-tasks and DA classification failures. A human study further highlights the significant gap between LLM and human-level dialogue understanding. These findings indicate that LLMs' shortcomings in dialogue comprehension hinder their ability to accurately predict DAs, highlighting the need for improved dialogue-aware training approaches.

Do LLMs Understand Dialogues? A Case Study on Dialogue Acts

Generative Reward Models (GenRMs) leverage synthesized Chains of Thought (CoT) to reduce the need for massive labeled data, but this approach introduces risks of overoptimization due to the inability to guarantee the correctness of the CoTs. Identifying and optimizing unexpected behaviors within these synthesized CoT remains a challenge, as it heavily depends on precise annotations of intermediate behavior, similar to process supervision. In this work, we introduce a criteria-based preference tree for reward modeling, where each path in the tree represents a reasoning trajectory based on synthesized criteria. Crucially, each reasoning trajectory can be independently optimized through RL algorithm. These fine-grained process reward signals are derived from the inference-time computations and predefined rules, eliminating the need for human supervision. In experiments, SyncPL showed significant improvements over baselines on multiple human preference benchmarks. We further demonstrate that synthesized data can be learned using a long CoT format, analogous to an o1-like model, further enhancing performance while keeping stability and efficiency during training.

Generative Reward Modeling via Synthetic Criteria Preference Learning

Large Language Models (LLMs) have shown remarkable performance across diverse tasks without domain-specific training, fueling interest in their potential for time-series forecasting. While LLMs have shown potential in zero-shot forecasting through prompting alone, recent studies suggest that LLMs lack inherent effectiveness in forecasting. Given these conflicting findings, a rigorous validation is essential for drawing reliable conclusions. In this paper, we evaluate the effectiveness of LLMs as zero-shot forecasters compared to state-of-the-art domain-specific models. Our experiments show that LLM-based zero-shot forecasters often struggle to achieve high accuracy due to their sensitivity to noise, underperforming even simple domain-specific models. We have explored solutions to reduce LLMs' sensitivity to noise in the zero-shot setting, but improving their robustness remains a significant challenge. Our findings suggest that rather than emphasizing zero-shot forecasting, a more promising direction would be to focus on fine-tuning LLMs to better process numerical sequences. Our experimental code is available at https://github.com/junwoopark92/revisiting-LLMs-zeroshot-forecaster.

Revisiting LLMs as Zero-Shot Time Series Forecasters: Small Noise Can Break Large Models

Radiology Report Generation (RRG) is an important research topic for relieving radiologists' heavy workload. Existing RRG models mainly rely on supervised fine-tuning (SFT) based on different model architectures using data pairs of radiological images and corresponding radiologist-annotated reports. Recent research has shifted focus to post-training improvements, aligning RRG model outputs with human preferences using reinforcement learning (RL). However, the limited data coverage of high-quality annotated data poses risks of overfitting and generalization. This paper proposes a novel Online Iterative Self-Alignment (OISA) method for RRG that consists of four stages: self-generation of diverse data, self-evaluation for multi-objective preference data, self-alignment for multi-objective optimization and self-iteration for further improvement. Our approach allows for generating varied reports tailored to specific clinical objectives, enhancing the overall performance of the RRG model iteratively. Unlike existing methods, our framework significantly increases data quality and optimizes performance through iterative multi-objective optimization. Experimental results demonstrate that our method surpasses previous approaches, achieving state-of-the-art performance across multiple evaluation metrics.

Online Iterative Self-Alignment for Radiology Report Generation

Large language models (LLMs) have encoded vast amounts of knowledge in their parameters, but the acquired knowledge can sometimes be incorrect or outdated over time, necessitating rectification after pre-training. Traditional localized methods in knowledge-based model editing (KME) typically assume that knowledge is stored in particular intermediate layers. However, recent research suggests that these methods do not identify the optimal locations for parameter editing, as knowledge gradually accumulates across all layers in LLMs during the forward pass rather than being stored in specific layers. This paper, for the first time, introduces the concept of critical transmission paths into KME for parameter updating. Specifically, these paths capture the key information flows that significantly influence the model predictions for the editing process. To facilitate this process, we also design a parameter-aware contrastive rectifying algorithm that considers less important paths as contrastive examples. Experiments on two prominent datasets and three widely used LLMs demonstrate the superiority of our method in editing performance.

Parameter-Aware Contrastive Knowledge Editing: Tracing and Rectifying based on Critical Transmission Paths

The rapid advancement of scientific progress requires innovative tools that can accelerate knowledge discovery. Although recent AI methods, particularly large language models (LLMs), have shown promise in tasks such as hypothesis generation and experimental design, they fall short of replicating the collaborative nature of real-world scientific practices, where diverse experts work together in teams to tackle complex problems. To address the limitations, we propose an LLM-based multi-agent system, i.e., Virtual Scientists (VIRSCI), designed to mimic the teamwork inherent in scientific research. VIRSCI organizes a team of agents to collaboratively generate, evaluate, and refine research ideas. Through comprehensive experiments, we demonstrate that this multi-agent approach outperforms the state-of-the-art method in producing novel scientific ideas. We further investigate the collaboration mechanisms that contribute to its tendency to produce ideas with higher novelty, offering valuable insights to guide future research and illuminating pathways toward building a robust system for autonomous scientific discovery. The code is available at https://github.com/open-sciencelab/Virtual-Scientists.

Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System

Rumor detection on social media has become an emerging topic. Traditional deep learning-based methods model rumors based on content, propagation structure, or user behavior, but these approaches are constrained by limited modeling capacity and insufficient training corpora. Recent studies have explored using LLMs for rumor detection through supervised fine-tuning (SFT), but face two issues: 1) unreliable samples sometimes mislead the model learning; 2) the model only learns the most salient input-output mapping and skips in-depth analyses of the rumored content for convenience. To address these issues, we propose an SFT-based LLM rumor detection model with Influence guided Sample selection and Game-based multi-perspective Analysis (ISGA). Specifically, we first introduce the Influence Score (IS) to assess the impact of samples on model predictions and select samples for SFT. We also approximate IS via Taylor expansion to reduce computational complexity. Next, we use LLMs to generate in-depth analyses of news content from multiple perspectives and model their collaborative process for prediction as a cooperative game. Then we utilize the Shapley value to quantify the contribution of each perspective for selecting informative perspective analyses. Experiments show that ISGA excels existing SOTA on three datasets.

Downloads

Next from ACL 2025

Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies

Similar lecture

Enhancing RLHF with Human Gaze Modeling

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES