China

Numerous datasets have been proposed to evaluate social bias in Natural Language Processing (NLP) systems. However, assessing bias within specific application domains remains challenging, as existing approaches often face limitations in scalability and domain adaptability. In this work, we introduce a domain-adaptive framework that utilizes prompting with Large Language Models (LLMs) to automatically transform template-based bias datasets into domain-specific variants. We apply our method to two widely used benchmarks—\textit{Equity Evaluation Corpus} (EEC) and \textit{Identity Phrase Templates Test Set} (IPTTS)—adapting them to the Twitter and Wikipedia Talk data. Our results show that the adapted datasets yield bias estimates more closely aligned with real-world data. These findings highlight the potential of LLM-based prompting as a domain-sensitive approach for bias evaluation in NLP systems. \footnote{Our code and data are \href{https://tinyurl.com/EMNLPBiasDomainAdaptAnonym}{available online}.}

EMNLP 2025

Adapting Bias Evaluation to Domain Contexts using Generative Models

and fairness

ethics

bias

## 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 user intentions in multi-turn dialogues is critical for conversational AI, yet existing approaches—relying on rigid slot-value structures or unstructured free-text—fail to fully capture conversational complexity. In this paper, we propose IntentionFrame, a semi-structured framework inspired by psychological and cognitive intention theories, which organizes conversational intents into four interrelated aspects: situation, emotion, action, and knowledge. This design not only retains interpretability but also provides LLMs with a rich context to accurately parse and respond to nuanced user inputs. To efficiently scale IntentionFrame annotations, we introduce a Weakly-supervised Reinforced Generation (WeRG) method that leverages a small set of high-quality human annotations in conjunction with abundant coarsely labeled data. By applying reinforcement learning to balance these diverse signals, WeRG aims to effectively generate reliable IntentionFrame annotations, which serve as essential grounding for downstream tasks—leading to substantial improvements in response generation and task completion. Our experiments, supported by both automatic metrics and human evaluations, show that integrating IntentionFrame with WeRG significantly improves LLMs’ conversational understanding and sets a new benchmark for intent analysis.

IntentionFrame: A Semi-Structured, Multi-Aspect Framework for Fine-Grained Conversational Intention Understanding

Controllable Dialogue Generation (CDG) enables chatbots to generate responses with desired attributes, and weighted decoding methods have achieved significant success in the CDG task. However, using a fixed constant value to manage the bias of attribute probabilities makes it challenging to find an ideal control strength that satisfies both controllability and fluency. To address this issue, we propose ECO decoding Entropy-based COntrol, which dynamically adjusts the control strength at each generation step according to the model’s entropy in both the language model and attribute classifier probability distributions. Experimental results on DailyDialog and MultiWOZ datasets show that our method achieves improved control accuracy while maintaining fluency and grammar, outperforming previous decoding methods across various models and settings. Furthermore, ECO decoding alleviates probability interpolation issues in multi-attribute generation, demonstrating its robust performance in both single and multi-attribute scenarios.

ECO Decoding: Entropy-Based Control for Controllability and Fluency in Controllable Dialogue Generation

Conversational Recommender Systems (CRSs) aim to elicit user preferences via natural dialogue to provide suitable item recommendations. However, current CRSs often deviate from realistic human interactions by rapidly recommending items in brief sessions. This work addresses this gap by leveraging Large Language Models (LLMs) to generate dialogue summaries from dialogue history and item recommendation information from item description. This approach enables the extraction of both explicit user statements and implicit preferences inferred from the dialogue context. We introduce a method using Direct Preference Optimization (DPO) to ensure dialogue summary and item recommendation information are rich in information crucial for effective recommendations. Experiments on two public datasets validate our method's effectiveness in fostering more natural and realistic conversational recommendation processes.

Refining Text Generation for Realistic Conversational Recommendation via Direct Preference Optimization

We introduce VoiceBBQ, a spoken extension of the BBQ benchmark that disentangles bias along two orthogonal axes: content and acoustic. The dataset converts every BBQ context into controlled voice conditions, enabling per-axis accuracy, bias, and consistency scores that remain comparable to the original text benchmark. Using Voice BBQ, we evaluate two SLMs—LLaMA-Omni and Qwen2-Audio—and observe sharp architectural contrasts: LLaMA-Omni retains strong acoustic sensitivity, amplifying gender and accent bias, whereas Qwen2-Audio substantially dampens these cues while preserving content fidelity. Voice BBQ thus provides a compact, drop-in testbed for jointly diagnosing textual and acoustic bias across spoken language models.

VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model

Extensive research on LLM-based spoken dialogue systems has significantly advanced the development of intelligent voice assistants. However, the integration of role information within speech remains an underexplored area, limiting its application in real-world scenarios, particularly in multi-party dialogue settings. With the growing demand for personalization, voice assistants that can recognize and remember users establish a deeper connection with them. We focus on enabling LLMs with speaker-awareness capabilities and enhancing their understanding of character settings through synthetic data to generate contextually appropriate responses. We introduce Persona-Dialogue, the first large-scale multi-party spoken dialogue dataset that incorporates speaker profiles. Based on this dataset, we propose PAChat, an architecture that simultaneously models both linguistic content and speaker features, allowing LLMs to map character settings to speaker identities in speech. Through extensive experiments, we demonstrate that PAChat successfully achieves speaker-specific responses, character understanding, and the generation of targeted replies in multi-party dialogue scenarios, surpassing existing spoken dialogue systems.

PACHAT: Persona-Aware Speech Assistant for Multi-party Dialogue

Considering the importance of detecting hateful language, labeled hate speech data is expensive and time-consuming to collect, particularly for low-resource languages. Prior work has demonstrated the effectiveness of cross-lingual transfer learning and data augmentation in improving performance on tasks with limited labeled data. To develop an efficient and scalable cross-lingual transfer learning approach, we leverage nearest-neighbor retrieval to augment minimal labeled data in the target language, thereby enhancing detection performance. Specifically, we assume access to a small set of labeled training instances in the target language and use these to retrieve the most relevant labeled examples from a large multilingual hate speech detection pool. We evaluate our approach on eight languages and demonstrate that it consistently outperforms models trained solely on the target language data. Furthermore, in most cases, our method surpasses the current state-of-the-art. Notably, our approach is highly data-efficient, retrieving as small as 200 instances in some cases while maintaining superior performance. Moreover, it is scalable, as the retrieval pool can be easily expanded, and the method can be readily adapted to new languages and tasks. We also apply maximum marginal relevance to mitigate redundancy and filter out highly similar retrieved instances, resulting in improvements in some languages.

Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data

Large Language Models (LLMs) exhibit strong performance across a wide range of NLP tasks, yet aligning their outputs with the principles of Helpfulness, Harmlessness, and Honesty (HHH) remains a persistent challenge. Existing methods often optimize for individual alignment dimensions in isolation, leading to trade-offs and inconsistent behavior. While Mixture-of-Experts (MoE) architectures offer modularity, they suffer from poorly calibrated routing, limiting their effectiveness in alignment tasks. We propose TrinityX, a modular alignment framework that incorporates a Mixture of Calibrated Experts (MoCaE) within the Transformer architecture. TrinityX leverages separately trained experts for each HHH dimension, integrating their outputs through a calibrated, task-adaptive routing mechanism that combines expert signals into a unified, alignment-aware representation. Extensive experiments on three standard alignment benchmarks—Alpaca (Helpfulness), BeaverTails (Harmlessness), and TruthfulQA (Honesty)—demonstrate that TrinityX outperforms strong baselines, achieving relative improvements of 32.5% in win rate, 33.9% in safety score, and 28.4% in truthfulness. In addition, TrinityX reduces memory usage and inference latency by over 40% compared to prior MoE-based approaches. Ablation studies highlight the importance of calibrated routing, and cross-model evaluations confirm TrinityX’s generalization across diverse LLM backbones. Our code is available at: \url{https://anonymous.4open.science/r/TrinityX-3265}

Too Helpful, Too Harmless, Too Honest or Just Right?

Large language models (LLMs) have achieved remarkable performance across diverse natural language processing tasks, but concerns persist regarding their potential political biases. While prior research has extensively explored political biases in LLMs' text generation and perception, scant attention has been devoted to biases associated with media outlet names. In this study, we systematically investigate the presence of media outlet name biases in LLMs and evaluate their impact on downstream tasks, such as political bias prediction and news summarization. Our findings demonstrate that LLMs consistently exhibit biases toward the known political leanings of media outlets, with variations across model families and scales. We propose a novel metric to quantify media outlet name biases in LLMs and leverage this metric to develop an automated prompt optimization framework. This framework effectively mitigates media outlet name biases, offering a scalable approach to enhancing the fairness of LLMs in news-related applications.

Measuring and Mitigating Media Outlet Name Bias in Large Language Models

Interaction between the learner and the feedback-giver has come into focus recently for post-training of Large Language Models (LLMs), through the use of reward models that judge the appropriateness of a model's response. In this paper, we investigate whether Dialogue Games---goal-directed and rule-governed activities driven predominantly by verbal actions---can also serve as a source of feedback signals for learning. We introduce Playpen, an environment for off- and online learning through Dialogue Game self-play, and investigate a representative set of post-training methods: supervised fine-tuning, direct alignment (DPO), and reinforcement learning with GRPO. We experiment with post-training a small LLM (Llama-3.1-8B-Instruct), evaluating performance on unseen instances of training games as well as unseen games, and on standard benchmarks. We find that imitation learning through SFT improves performance on unseen instances, but negatively impacts other skills, while interactive learning with GRPO shows balanced improvements without loss of skills. We release the framework and the baseline training setups to foster research in this promising new direction of ``learning in (synthetic) interaction''

Playpen: An Environment for Exploring Learning From Dialogue Game Feedback

Large language models (LLMs) offer a powerful opportunity to simulate the results of social science experiments. In this work, we demonstrate that finetuning LLMs directly on individual-level responses from past experiments meaningfully improves the accuracy of such simulations across diverse social science domains. We construct SocSci210 via an automatic pipeline, a dataset comprising 2.9 million responses from 400,491 participants in 210 open-source social science experiments. Through finetuning, we achieve multiple levels of generalization. In completely unseen studies, our strongest model, Socrates-Qwen-14B, produces predictions that are 26% more aligned with distributions of human responses to diverse outcome questions under varying conditions relative to its base model (Qwen2.5-14B), outperforming GPT-4o by 13%. By finetuning on a subset of conditions in a study, generalization to new unseen conditions is particularly robust, improving by 71%. Since SocSci210 contains rich demographic information, we reduce demographic parity difference, a measure of bias, by 10.6% through finetuning. Because social sciences routinely generate rich, topic-specific datasets, our findings indicate that finetuning on such data could enable more accurate simulations for experimental hypothesis screening. We release our data, models and finetuning code at stanfordhci.github.io/socrates.

Downloads

Next from EMNLP 2025

IntentionFrame: A Semi-Structured, Multi-Aspect Framework for Fine-Grained Conversational Intention Understanding

Similar lecture

What's Not Said Still Hurts: A Description-Based Evaluation Framework for Measuring Social Bias in LLMs