China

Evaluating social biases in language models (LMs) is crucial for ensuring fairness and minimizing the reinforcement of harmful stereotypes in AI systems. Existing benchmarks, such as the Bias Benchmark for Question Answering (BBQ), primarily focus on Western contexts, limiting their applicability to the Indian context. To address this gap, we introduce BharatBBQ, a culturally adapted benchmark designed to assess biases in Hindi, English, Marathi, Bengali, Tamil, Telugu, Odia, and Assamese. BharatBBQ covers 13 social categories, including 3 intersectional groups, reflecting prevalent biases in the Indian sociocultural landscape. Our dataset contains 49,108 examples in one language that are expanded using translation and verification to 392,864 examples in eight different languages. We evaluate five multilingual LM families across zero and few-shot settings, analyzing their bias and stereotypical bias scores. Our findings highlight persistent biases across languages and social categories and often amplified biases in Indian languages compared to English, demonstrating the necessity of linguistically and culturally grounded benchmarks for bias evaluation.

EMNLP 2025

BharatBBQ: A Multilingual Bias Benchmark for Question Answering in the Indian Context

technical paper

## 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.

With the help of in-context learning (ICL), large language models (LLMs) have achieved impressive performance across various tasks. However, the function of descriptive instructions during ICL remains under-explored. In this work, we propose an ensemble prompt framework to describe the selection criteria of multiple in-context examples, and preliminary experiments on machine translation (MT) across six translation directions confirm that this framework boosts ICL performance. But to our surprise, LLMs might not care what the descriptions actually say, and the performance gain is primarily caused by the ensemble format, since it could lead to improvement even with random descriptive nouns. We further apply this new ensemble framework on a range of commonsense, math, logical reasoning and hallucination tasks with three LLMs and achieve promising results, suggesting again that designing a proper prompt format would be much more effective and efficient than paying effort into specific descriptions. Our code will be publicly available once this paper is published.

Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions

Adaptive learning focuses on recommending personalized materials (e.g., exercises, courses) to the unique needs of learners. Despite significant research, these methods still lag behind real teachers including two main limitations: (1) Prior methods model learner-item interactions based only on ID sequences, leading to insufficient use of both learner and item information, particularly the inability to leverage semantic content from item text; (2) The data-driven reinforcement learning frameworks struggle with stable performance in scenarios with sparse learning logs. To address these challenges, we introduce the Retrieval-enhanced Agent for Adaptive Learning (ReAL) powered by large language models (LLMs), to simulate teacher decision-making with extensive prior knowledge and teaching experience. Specifically, we approach the simulation from both internal and external perspectives. From the internal perspective, we utilize the superior natural language standing ability of LLMs to analyze item texts and learner profiles. This mechanism contributes to the generation of personalized and appropriate item candidates. From the external perspective, we simulate the teacher experience by retrieving similar learners, further ensuring the model's performance on sparse interaction data. Furthermore, we design a reflector based on learners' feedback to refine the recommendation process. Evaluation on three real-world datasets demonstrates the superiority of ReAL in both data utilization, recommendation accuracy and stability compared to various representative baselines.

ReAL: How Can LLMs Simulate the Real Teacher? Retrieval-enhanced Agent for Adaptive Learning

Large language models (LLMs) typically undergo instruction tuning to enhance alignment. Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs. However, how to evolve these selected subsets alongside the development of new instruction data remains insufficiently explored. To achieve LLMs' ongoing alignment, we introduce Instruction Bank (InsBank), a continuously updated repository that integrates the latest valuable instruction data. We further propose Progressive Instruction Bank Evolution (PIBE), a novel framework designed to evolve InsBank effectively and efficiently over time. PIBE employs a gradual data selection strategy to maintain long-term efficiency, leveraging a representation-based diversity score to capture relationships between data points and retain historical information for comprehensive diversity evaluation. This also allows for flexible combination of diversity and quality scores during data selection and ranking. Extensive experiments demonstrate that PIBE significantly outperforms baselines in InsBank evolution and is able to extract budget-specific subsets, demonstrating its effectiveness and adaptability.

InsBank: Evolving Instruction Subset for Ongoing Alignment

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. Math Word Problems (MWPs) serve as a crucial benchmark for evaluating LLMs' reasoning abilities. While most research primarily focuses on improving accuracy, it often neglects understanding and addressing the underlying patterns of errors. Current error classification methods rely on static and predefined categories, which limit their ability to capture the full spectrum of error patterns in mathematical reasoning. To enable systematic error analysis, we collect error samples from 15 different LLMs of varying sizes across four distinct MWP datasets using multiple sampling strategies. Based on this extensive collection, we introduce MWPES-300K, a comprehensive dataset containing 304,865 error samples that cover diverse error patterns and reasoning paths. To reduce human bias and enable fine-grained analysis of error patterns, we propose a novel framework for automated dynamic error classification in mathematical reasoning. Experimental results demonstrate that dataset characteristics significantly shape error patterns, which evolve from basic to complex manifestations as model capabilities increase. With deeper insights into error patterns, we propose Error-Aware Prompting (EAP) that incorporates common error patterns as explicit guidance, leading to significant improvements in mathematical reasoning performance.

Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework

Enhancing large language models (LLMs) with external tools has become a promising approach for solving complex tasks. As the number of available tools grows, context-based prompting methods increasingly rely on retrieval mechanisms. A common solution is to represent each tool with a unique token and train LLMs to generate the corresponding token during inference. However, this approach suffers from linear growth in representation space, leading to scalability challenges. It also limits generalization to novel or rare tools and underutilizes collaborative signals among tools in downstream tasks. In this paper, we propose SGTC, a generative tool invocation framework that introduces structure-aware semantic tokenization to encode tools as discrete code sequences. This method ensures similar tools share subtokens, enabling compression of the representation space and facilitating token sharing for new tools. We further introduce a post-guided, multistage iterative training strategy on a shared backbone model, where collaborative signals from downstream tasks guide the dynamic refinement of tool representations. Extensive experiments on the ToolBench dataset, which includes over 47,000 APIs, demonstrate the effectiveness of SGTC across various tasks, showcasing its potential as a scalable and generalizable generative tool-using paradigm in large-scale tool usage scenarios.

Toolscaler: Scalable Generative Tool Calling via Structure-Aware Semantic Tokenization

Auctions are a vital economic mechanism used to determine the market value of goods or services through competitive bidding within a specific framework. However, much of the current research primarily focuses on the bidding algorithms used within auction mechanisms. This often neglects the potential benefits of incorporating individual users' unique preferences into the valuation process. Our theoretical and empirical analysis demonstrates that valuation errors can significantly impact the overall utility. To bridge this gap, we propose a personalized valuation framework, namely Large \underline{La}nguage \underline{M}odels-powered \underline{P}ersonalized \underline{Val}uation (LaMP-Val), which integrates Large Language Models to incorporate personalized semantic preference into users valuation process. LaMP-Val integrating three components: data, learning, and evaluation. The data component tackles the challenge of building a novel dataset specifically for LLMs fine-tuning in personalized valuation modeling. The learning component introduces a diversity template to enhance LLMs' capacity for modeling fine-grained personal valuation patterns. The evaluation component establishes a closed-loop system where LLM-generated valuations interact with bidding strategies and auction. It proposes two novel metrics to quantify valuation precision and bidding intention accuracy in personalized scenarios. Extensive experiments show that LaMP-Val more accurately captures personalized values and achieves greater profits than baseline approaches.

LaMP-Val: Large Language Models Empower Personalized Valuation in Auction

In web search scenarios, erroneous queries frequently degrade users' experience through irrelevant results, underscoring the pivotal role of Chinese Spelling Check (CSC) systems. Although large language models (LLMs) exhibit remarkable capabilities across many tasks, they face critical challenges in the CSC scenario: (1) poor generalization to rare entities in open-domain searches, and (2) failure to adapt to temporal entity variations due to static parameters, resulting in serious over-correction issues. To tackle this, we present RACQC, a **C**hinese **Q**uery **C**orrection system with **R**etrieval-**A**ugmented Generation(RAG) and multi-task learning. Specifically, our approach (1) integrates dynamic knowledge retrieval through entity-centric RAG to address rare entities and innovatively proposes an entity-title collaborative corpus, and (2) employs contrastive correction tasks to mitigate LLM over-correction tendencies. Furthermore, we propose MDCQC, a **M**ulti-**D**omain **C**hinese **Q**uery **C**orrection benchmark to test the model's entity correction capabilities. Extensive experiments on several datasets show that RACQC significantly outperforms existing baselines in CSC tasks. Specifically, RACQC achieves a maximum improvement of +9.92% on the search scenario benchmark and +3.2% on the general-domain dataset under the F₁ metric.

RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correction

Search engines play a central role in how people gather information, but subtle cues like headline framing may influence not only what users believe but also how they search. While framing effects on judgment are well documented, their impact on subsequent search behavior is less understood. We conducted a controlled experiment where participants issued queries and selected from headlines filtered by specific linguistic frames. Headline framing significantly shaped follow-up queries: conflict and strategy frames disrupted alignment with prior selections, while episodic frames led to more concrete queries than thematic ones. We also observed modest short-term frame persistence that declined over time. These results suggest that even brief exposure to framing can meaningfully alter the direction of users’ information-seeking behavior.

The Power of Framing: How News Headlines Guide Search Behavior

Despite the significant advancements of self-play fine-tuning (SPIN), which can transform a weak large language model (LLM) into a strong one through competitive interactions between models of varying capabilities, it still faces challenges in the Text-to-SQL task. SPIN does not generate new information, and the large number of correct SQL queries produced by the opponent model during self-play reduces the main model's ability to generate accurate SQL queries. To address this challenge, we propose a new self-play fine-tuning method tailored for the Text-to-SQL task, called SPFT-SQL. Prior to self-play, we introduce a verification-based iterative fine-tuning approach, which synthesizes high-quality fine-tuning data iteratively based on the database schema and validation feedback to enhance model performance, while building a model base with varying capabilities. During the self-play fine-tuning phase, we propose an error-driven loss method that incentivizes incorrect outputs from the opponent model, enabling the main model to distinguish between correct SQL and erroneous SQL generated by the opponent model, thereby improving its ability to generate correct SQL. Extensive experiments and in-depth analyses on six open-source LLMs and five widely used benchmarks demonstrate that our approach outperforms existing state-of-the-art (SOTA) methods.

SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning

The wide adoption of Large Language Models (LLMs) has attracted significant attention from jailbreak attacks, where adversarial prompts crafted through optimization or manual design exploit LLMs to generate malicious contents. However, optimization-based attacks have limited efficiency and transferability, while existing manual designs are either easily detectable or demand intricate interactions with LLMs. In this paper, we first point out a novel perspective for jailbreak attacks: LLMs are more responsive to positive prompts. Based on this, we deploy Happy Ending Attack (HEA) to wrap up a malicious request in a scenario template involving a positive prompt formed mainly via a happy \ ending, it thus fools LLMs into jailbreaking either immediately or at a follow-up malicious request. This has made HEA both efficient and effective, as it requires only up to two turns to fully jailbreak LLMs. Extensive experiments show that our HEA can successfully jailbreak on state-of-the-art LLMs, including GPT-4o, Llama3-70b, Gemini-pro, and achieves 88.79\% attack success rate on average. We also provide quantitative explanations for the success of HEA.

Downloads

Next from EMNLP 2025

Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES