China

As large language models (LLMs) grow more capable, they face increasingly diverse and complex tasks, making reliable evaluation challenging. The paradigm of LLMs as judges has emerged as a scalable solution, yet prior work primarily focuses on simple settings. Their reliability in complex tasks—where multi-faceted rubrics, unstructured reference answers, and nuanced criteria are critical—remains understudied. In this paper, we constructed ComplexEval Bench, a challenge benchmark designed to systematically expose and quantify Auxiliary Information Induced Biases. We systematically investigated and validated 6 previously unexplored biases across 12 basic and 3 advanced scenarios. Key findings reveal: (1) all evaluated models exhibit significant susceptibility to these biases, with bias magnitude scaling with task complexity; (2) notably, Large Reasoning Models (LRMs) show paradoxical vulnerability. Our in-depth analysis offers crucial insights for improving the accuracy and verifiability of evaluation signals, paving the way for more general and robust evaluation models.

EMNLP 2025

Curse of Knowledge: Your Guidance and Provided Knowledge are biasing LLM Judges in Complex Evaluation

poster

## 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*

[**Link to Conference Handbook**](https://drive.google.com/file/d/1johU5QqVVYO4RfH7QcIORr7qrVBdzdwC/view?usp=sharing)





<br>

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

Alzheimer's Disease (AD), the 7th leading cause of death globally, demands scalable methods for early detection. While speech-based diagnostics offer promise, existing approaches struggle with temporal-spatial (T-S) challenges in capturing subtle linguistic shifts across different disease stages (temporal) and in adapting to cross-linguistic variability (spatial). This study introduces an LLM-driven T-S fusion, a novel framework that synergizes multilingual large language models (LLMs), contrastive learning, and interpretable marker discovery to revolutionize LOAD (Late-Onset AD) detection. Our key innovations include: (1) T-S Data Imputation: Leveraging LLMs to generate synthetic speech transcripts across different LOAD stages (NC, eMCI, lMCI, LOAD) and languages (Chinese/English/Spanish), addressing data scarcity while preserving clinical relevance (expert validation: 86% agreement with LLM-generated labels). (2) T-S Transformer with Contrastive Learning: A multilingual model that disentangles stage-specific (temporal) and language-specific (spatial) patterns, achieving a notable improvement of 10.9–24.7% in F1-score over existing baselines. (3) Cross-Linguistic Marker Discovery: Identifying language-agnostic markers and language-specific patterns to enhance interpretability for clinical adoption. By unifying temporal LOAD stages and spatial diversity, our framework achieves state-of-the-art performance in early LOAD detection while enabling cross-linguistic diagnostics. This study bridges NLP and clinical neuroscience, demonstrating LLMs' potential to amplify limited biomedical data and advance equitable healthcare AI.

An LLM-based Temporal-spatial Data Generation and Fusion Approach for Early Detection of Late Onset Alzheimer's Disease (LOAD) Stagings Especially in Chinese and English-speaking Populations

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle to scale to larger models and open-ended generation tasks. To address these limitations, this paper proposes BiasFilter, a model-agnostic, inference-time debiasing framework that integrates seamlessly with both open-source and API-based LLMs. Instead of relying on retraining with balanced data or modifying model parameters, BiasFilter enforces fairness by filtering generation outputs in real time. Specifically, it periodically evaluates intermediate outputs every few tokens, maintains an active set of candidate continuations, and incrementally completes generation by discarding low-reward segments based on a fairness reward signal. To support this process, we construct a fairness preference dataset and train an implicit reward model to assess token-level fairness in generated responses. Extensive experiments demonstrate that BiasFilter effectively mitigates social bias across a range of LLMs while preserving overall generation quality.

BiasFilter: An Inference-Time Debiasing Framework for Large Language Models

Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying subjectivity in recognizing the human values that motivate arguments. We evaluate two main approaches: inferring subjectivity through value prediction vs. directly identifying subjectivity. Our experiments show that direct subjectivity identification significantly improves the model performance of flagging subjective arguments. Furthermore, combining contrastive loss with binary cross-entropy loss does not improve performance but reduces the dependency on per-label subjectivity. Our proposed methods can help identify arguments that individuals may interpret differently, fostering a more nuanced annotation process.

Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments

Users of Augmentative and Alternative Communication (AAC) may write letter-by-letter via an interface that uses a character language model. However, most state-of-the-art large pretrained language models predict subword tokens of variable length. We investigate how to practically use such models to make accurate and efficient character predictions. We fine-tune models using a large dataset of sentences we curated in which each sentence is rated according to how useful it might be for spoken or written AAC communication. We find that using an algorithm to produce character predictions from a subword large language model provides more accurate predictions than adding a classification layer or using a byte-level model. We also find that our domain adaptation procedure is effective at improving model performance on simple, conversational text.

Adapting Large Language Models for Character-based Augmentative and Alternative Communication

Cognitive science offers rich theories of learning and communication, yet these are often difficult to operationalize at scale. We demonstrate how natural language processing can bridge this gap by applying psycholinguistic theories of discourse to real-world educational data. We investigate linguistic alignment - the convergence of conversational partners’ word choice, grammar, and meaning - as a measure of interactive alignment. Using a longitudinal dataset of real-world tutoring interactions and associated student test scores, we examine (1) the extent of alignment, (2) role-based patterns among tutors and students, and (3) the relationship between alignment and learning outcomes. We find that both tutors and students exhibit lexical, syntactic, and semantic alignment, with tutors aligning more strongly overall. Crucially, lexical alignment predicts student learning gains. As a lightweight, interpretable, metric, linguistic alignment offers practical applications in intelligent tutoring systems, educator dashboards, and tutor training.

Linguistic Alignment Predicts Learning in Small Group Tutoring Sessions

Large Language Models (LLMs) excel in Natural Language Processing (NLP) tasks but often propagate societal biases from their training data, leading to discriminatory outputs. These biases are amplified by the models' self-attention mechanisms, which disproportionately emphasize biased correlations with sensitive tokens, like "he" or "she", reflecting the sensitive attributes such as gender and race. To address this issue, we propose a novel fine-tuning method, called Cross-Attention-based Weight Decay (CrAWD), which modifies the LLM architecture to mitigate bias. CrAWD introduces a cross-attention mechanism between an input sequence and a sensitive token sequence, enabling the model to identify and selectively decay the attention weights of tokens associated with sensitive tokens. This reduces the influence of biased association on the model's generation while maintaining task performance. Evaluations on real-world datasets demonstrate the effectiveness of our proposed CrAWD method. Notably, our method can handle multiple sensitive attributes by adjusting the sensitive token sequence, and it does not require full knowledge of sensitive tokens presented in the dataset, underscoring CrAWD's versatility in promoting fair LLMs across various applications.

Fine-tuning LLMs with Cross-Attention-based Weight Decay for Bias Mitigation

Responsible use of Authorship Verification (AV) systems not only requires high accuracy but also interpretable solutions. More importantly, for systems to be used to make decisions with real-world consequences requires the model's prediction to be explainable using interpretable features that can be traced to the original texts. Neural methods achieve high accuracies, but their representations lack direct interpretability. Furthermore, LLM predictions cannot be explained faithfully -- if there is an explanation given for a prediction, it doesn't represent the reasoning process behind the model's prediction. In this paper, we introduce Residualized Similarity (RS), a novel method that supplements systems using interpretable features with a neural network to improve their performance while maintaining interpretability. Authorship verification is fundamentally a similarity task, where the goal is to measure how alike two documents are. The key idea is to use the neural network to predict a residual similarity, i.e. the error in the similarity predicted by the interpretable system. Our evaluation across four datasets shows that not only can we match the performance of state-of-the-art authorship verification models, but we can show how and to what degree the final prediction is faithful and interpretable.

Residualized Similarity for Faithfully Explainable Authorship Verification

Academic question answering (QA) in heterogeneous scholarly networks presents unique challenges requiring both structural understanding and interpretable reasoning. While graph neural networks (GNNs) capture structured graph information and large language models (LLMs) demonstrate strong capabilities in semantic comprehension, current approaches lack integration at the reasoning level. We propose HetGCoT, a framework enabling LLMs to effectively leverage and learn information from graphs to reason interpretable academic QA results. Our framework introduces three technical contributions: (1) a framework that transforms heterogeneous graph structural information into LLM-processable reasoning chains, (2) an adaptive metapath selection mechanism identifying relevant subgraphs for specific queries, and (3) a multi-step reasoning strategy systematically incorporating graph contexts into the reasoning process. Experiments on OpenAlex and DBLP datasets show our approach outperforms all sota baselines. The framework demonstrates adaptability across different LLM architectures and applicability to various scholarly question answering tasks.

HetGCoT: Heterogeneous Graph-Enhanced Chain-of-Thought LLM Reasoning for Academic Question Answering

Large Language Models (LLMs) have recently emerged as promising tools for knowledge tracing due to their strong reasoning and generalization abilities. While recent LLM-based KT methods have introduced new prompt formats, they struggle to reflect the histories of example learners within a single prompt during in-context learning (ICL), leading to limited scalability and high computational cost under token constraints. In this work, we present \textit{LLM-based Option weighted Knowledge Tracing (LOKT)}, a simple yet effective LLM-based knowledge tracing framework that encodes the interaction histories of example learners in context as \textit{textual categorical option weights (TCOW)}. These are semantic labels (e.g., “inadequate”) assigned to the options selected by learners when answering questions helping understand LLM. Experiments on multiple-choice datasets show that LOKT outperforms existing LLM-based KT models in both warm-start and few-shot settings. Moreover, LOKT enables scalable and cost-efficient inference, performing strongly even under strict token constraints. Our code is available at https://anonymous.4open.science/r/LOKT_model-3233

Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing

In-context learning (ICL) in Large Language Models (LLMs) has shown remarkable performance across various tasks without requiring fine-tuning. However, recent studies have highlighted the risk of private data leakage through the prompt in ICL, especially when LLMs are exposed to malicious attacks. While differential privacy (DP) provides strong privacy guarantees, it often significantly reduces the utility of in-context learning (ICL). To address this challenge, we incorporate task-related public data into the ICL framework while maintaining the DP guarantee. Based on this approach, we propose a private in-context learning algorithm that effectively balances privacy protection and model utility. Through experiments, we demonstrate that our approach significantly improves the utility of private ICL with the assistance of public data. Additionally, we show that our method is robust against membership inference attacks, demonstrating empirical privacy protection.

Downloads

Next from EMNLP 2025

An LLM-based Temporal-spatial Data Generation and Fusion Approach for Early Detection of Late Onset Alzheimer's Disease (LOAD) Stagings Especially in Chinese and English-speaking Populations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES