China

Research ideation is crucial for scientific progress, but the exponential increase in scientific literature makes it challenging to stay updated and identify impactful directions. Recent developments in large language models(LLMs) offer a promising avenue to automate this process. However, existing methods for idea generation either trivially prompt LLMs or expose LLMs to extensive literature without indicating useful information. Inspired by human research processes, we propose a Chain-of-Ideas~(CoI) agent, an LLM-based agent that organizes relevant literature in a chain structure to effectively mirror the progressive development in a research domain. This organization helps LLMs better grasp current advancements, thereby improving ideation capabilities. Further, we present Idea Arena, a protocol for evaluating idea-generation methods from different perspectives, which aligns closely with the preferences of human researchers. Experiments show that CoI agent consistently outperforms existing methods and matches human quality in idea generation. Moreover, CoI agent is budget-friendly, requiring only $0.50 to generate a candidate idea and its experimental design.

EMNLP 2025

Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents

llm;agent;idea generation

## 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."<br>

*Message from the General Chair, Dirk Hovy*





<br>

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

poster

Understanding event relationships is critical for tasks such as narrative comprehension, information extraction, and reasoning in natural language processing. Despite the remarkable advancements of large language models (LLMs) across diverse NLP tasks, current studies have not systematically evaluated their ability to capture the complex of event relations. To this end, we aim to assess LLMs on event relationship extraction (ERE) by designing the benchmark EventRelBench. EventRelBench comprises 35K diverse event relation questions covering four key categories—coreference, temporal, causal, and supersub relations. These questions are provided at two levels of granularity: document‐level and sentence‐level. Extensive experiments on different sizes and types of LLMs show that existing LLMs still fall short in accurately extracting and understanding event relationships. To address this gap, we introduce EventRelInst, a 48K instruction fine‑tuning dataset in the event relation extraction domain. Experimental results not only highlight the shortcomings of current general-purpose LLMs in extracting event relationships but also demonstrate the effectiveness of EventRelInst. Both EventRelBench and EventRelBench will be publicly available.

EventRelBench: A Comprehensive Benchmark for Evaluating Event Relation Understanding in Large Language Models

The performance of pre-trained Large Language Models (LLMs) is often sensitive to nuances in prompt templates, requiring careful prompt engineering, adding costs in terms of computing and human effort. In this study, we present experiments encompassing multiple LLMs variants of varying sizes aimed at probing their preference with different prompts. Through experiments on Question Answering, we show prompt preference consistency across LLMs of different sizes. We also show that this consistency extends to other tasks, such as Natural Language Inference. Utilizing this consistency, we propose a method to use a smaller model to select effective prompt templates for a larger model. We show that our method substantially reduces the cost of prompt engineering while consistently matching performance with optimal prompts among candidates. More importantly, our experiment shows the efficacy of our strategy across fourteen LLMs and its applicability to a broad range of NLP tasks, highlighting its robustness.

S2LPP: Small-to-Large Prompt Prediction across LLMs

Medical domain automated text generation is an active area of research and development; however, evaluating the clinical quality of generated reports remains a challenge, especially in instances where domain-specific metrics are lacking, e.g. histopathology. We propose HARE (Histopathology Automated Report Evaluation), a novel entity and relation centric framework, composed of a benchmark dataset, a named entity recognition (NER) model, a relation extraction (RE) model, and a novel metric, which prioritizes clinically relevant content by aligning critical histopathology entities and relations between reference and generated reports. To develop the HARE benchmark, we annotated 854 de-identified diagnostic histopathology reports from a hospital and 652 reports from The Cancer Genome Atlas (TCGA) with domain-specific entities and relations. We fine-tuned GatorTronS, a domain-adapted language model to develop HARE-NER and HARE-RE which achieved the highest NER F1-score (0.865) and highest RE F1-score (0.988) among the tested models. The proposed HARE metric outperformed traditional metrics including ROUGE and Meteor, as well as radiology metrics such as RadGraph-XL, with the highest correlation and the best regression to expert evaluations (higher than the second best method, GREEN, a large language model based radiology report evaluator, by Pearson r = 0.212, Spearman ρ = 0.189, Kendall τ = 0.151, R² = 0.23, RMSE = 0.024). We will release HARE, datasets, and the models to foster advancements in histopathology report generation, providing a robust framework for improving the quality of reports.

HARE: an entity and relation centric evaluation framework for histopathology reports

Metrics like FactScore and VeriScore that evaluate long-form factuality operate by decomposing an input response into atomic claims and then individually verifying each claim. While effective and interpretable, these methods incur numerous LLM calls and can take upwards of 100s to evaluate a single response, limiting their practicality in large-scale evaluation and training scenarios. To address this, we propose VeriFastScore, which leverages synthetic data to fine-tune Llama3.1 8B for simultaneously extracting and verifying all verifiable claims within a given text based on evidence from Google Search. We show that this task cannot be solved via few-shot prompting with closed LLMs due to its complexity: the model receives sim4K tokens of evidence on average and needs to concurrently decompose claims, judge their verifiability, and verify them against noisy evidence. However, our fine-tuned VeriFastScore model demonstrates strong correlation with the original VeriScore pipeline at both the example level (r=0.80) and system level (r=0.94) while achieving an overall speedup of 6.6times (9.9 times excluding evidence retrieval) over VeriScore. To facilitate future factuality research, we publicly release our VeriFastScore model and synthetic datasets.

VeriFastScore: Speeding up long-form factuality evaluation

Ensuring consistent safety across multiple languages remains a significant challenge for large language models (LLMs). We introduce Soteria, a lightweight yet powerful strategy that locates and minimally adjusts the “functional heads” most responsible for harmful content generation in each language. By altering only a fraction of parameters, Soteria drastically reduces policy violations without sacrificing overall model performance, even in low-resource settings. To rigorously evaluate our approach, we also present XThreatBench, a specialized multilingual dataset capturing fine-grained harmful behaviors drawn from real policy guidelines. Experiments with leading open-source LLMs (e.g., Llama, Qwen, Mistral) show that Soteria consistently improves safety metrics across high-, mid-, and low-resource languages. These findings highlight a promising path toward scalable, linguistically attuned, and ethically aligned LLMs worldwide. We will make the dataset and source code publicly available upon acceptance.

Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment

Mental health issues are worsening in today's competitive society, such as depression and anxiety. Traditional healings like counseling and chatbots fail to engage effectively, they often provide generic responses lacking emotional depth. Although large language models (LLMs) have the potential to create more human-like interactions, they still struggle to capture subtle emotions. This requires LLMs to be equipped with human-like adaptability and warmth. To fill this gap, we propose the MIND (Multi-agent INner Dialogue), a novel paradigm that provides more immersive psychological healing environments. Considering the strong generative and role-playing ability of LLM agents, we predefine an interactive healing framework and assign LLM agents different roles within the framework to engage in interactive inner dialogues with users, thereby providing an immersive healing experience. We conduct extensive human experiments in various real-world healing dimensions, and find that MIND provides a more user-friendly experience than traditional paradigms. This demonstrates that MIND effectively leverages the significant potential of LLMs in psychological healing.

MIND: Towards Immersive Psychological Healing with Multi-Agent Inner Dialogue

The rapid development of advanced large language models (LLMs) has made AI-generated text indistinguishable from human-written text. Previous work on detecting AI-generated text has made effective progress, but has not involved modern Chinese poetry. Due to the distinctive characteristics of modern Chinese poetry, it is difficult to identify whether a poem originated from humans or AI. Therefore, it is of great practical significance to develop reliable poetry source identification technology. Yet, there is currently no research on the detection of modern Chinese poetry. Based on the urgency of identifying AI-generated poetry in the real Chinese world, this paper proposes a novel benchmark for detecting LLMs-generated modern Chinese poetry. We first construct a high-quality dataset comprising poems written by professional poets and those generated by multiple mainstream LLMs. Subsequently, we conduct systematic performance assessments of six detectors on this dataset. Experimental results demonstrate that current detectors cannot be used as reliable tools to detect modern Chinese poems generated by LLMs. The most difficult poetic features to detect are intrinsic qualities, especially style. The detection results verify the effectiveness and necessity of our proposed benchmark. Our work lays a foundation for future tasks of detecting AI-generated poems.

Benchmarking the Detection of LLMs-Generated Modern Chinese Poetry

LLM-as-a-Judge employs large language models (LLMs), such as GPT-4, to evaluate the quality of LLM-generated responses, gaining popularity for its cost-effectiveness and strong alignment with human evaluations. However, training proxy judge models using evaluation data generated by powerful teacher models introduces a critical yet previously overlooked issue: teacher preference bias, where the proxy judge model learns a biased preference for responses from the teacher model. To tackle this problem, we propose a novel setting that incorporates an additional assistant model, which is not biased toward the teacher model's responses, to complement the training data. Building on this setup, we introduce AGDe-Judge, a three-stage framework designed to debias from both the labels and feedbacks in the training data. Extensive experiments demonstrate that AGDe-Judge effectively reduces teacher preference bias while maintaining strong performance across six evaluation benchmarks. \footnote{Code is available at \url{https://anonymous.4open.science/r/AGDe-Judge-E352 }.}.

Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge

The Key-Value (KV) cache reading latency increases significantly with context lengths, hindering the efficiency of long-context LLM inference. To address this, previous works propose retaining a small fraction of KV cache based on token importance. For example, KV eviction uses static heuristics to retain tokens, while KV retrieval dynamically selects query-relevant tokens for more adaptive cache management. However, we observe that important tokens are often sparsely distributed across the long context. This sparsity makes existing page-level KV retrieval inaccurate, as each page may include irrelevant tokens and miss critical ones. In this work, we propose Fier, a **Fi**ne-Grained and **E**fficient KV cache **R**etrieval method. Fier uses 1-bit quantized keys to estimate the importance of each token, resulting in efficient and precise retrieval. Experiments show that Fier matches full KV performance using only 11\% of the cache budget across various long-context tasks, reducing decoding latency by 1.2times to 1.5times.

FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference

Figure captions are crucial for helping readers understand and remember a figure's key message. Many models have been developed to generate these captions, helping authors compose better quality captions more easily. Yet, authors almost always need to revise generic AI-generated captions to match their writing style and the domain's style, highlighting the need for personalization. Despite language models' personalization (LaMP) advances, these technologies often focus on text-only settings and rarely address scenarios where both inputs and profiles are multimodal. This paper introduces LaMP-Cap, a dataset for personalized figure caption generation with multimodal figure profiles. For each target figure, LaMP-Cap provides not only the needed inputs, such as figure images, but also up to three other figures from the same document—each with its image, caption, and figure-mentioning paragraphs—as a profile to characterize the context. Experiments with four LLMs show that using profile information consistently helps generate captions closer to the original author-written ones. Ablation studies reveal that images in the profile are more helpful than figure-mentioning paragraphs, highlighting the advantage of using multimodal profiles over text-only ones.

Downloads

Next from EMNLP 2025

EventRelBench: A Comprehensive Benchmark for Evaluating Event Relation Understanding in Large Language Models

Similar lecture

Agent Laboratory: Using LLM Agents as Research Assistants