China

Modern automatic speech recognition (ASR) models, such as OpenAI’s Whisper, rely on deep encoder-decoder architectures, and their encoders are a critical bottleneck for efficient deployment due to high computational intensity. We introduce a low-rank compression scheme for ASR encoders that significantly reduces inference costs while maintaining transcription accuracy. Our approach leverages the strong low-rank properties observed in intermediate activations: by applying principal component analysis (PCA) with a small calibration data set, we approximate linear transformations with a chain of low-rank matrix multiplications, and further optimize self-attention to work in the reduced dimension. Evaluation results show that our method can compress Whisper large-v3&#39;s encoder size by over 50%, matching Whisper medium&#39;s size with better transcription accuracy, thereby establishing a new Pareto-optimal frontier of efficiency and performance.

EMNLP 2025

LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

efficiency

automatic speech recognition

pruning

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

NAACL 2025

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Modern automatic speech recognition (ASR) models, such as OpenAI’s Whisper, rely on deep encoder-decoder architectures, and their encoders are a critical bottleneck for efficient deployment due to high computational intensity. We introduce a low-rank compression scheme for ASR encoders that significantly reduces inference costs while maintaining transcription accuracy. Our approach leverages the strong low-rank properties observed in intermediate activations: by applying principal component analysis (PCA) with a small calibration data set, we approximate linear transformations with a chain of low-rank matrix multiplications, and further optimize self-attention to work in the reduced dimension. Evaluation results show that our method can compress Whisper large-v3's encoder size by over 50%, matching Whisper medium's size with better transcription accuracy, thereby establishing a new Pareto-optimal frontier of efficiency and performance.

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." 

*Message from the General Chair, Dirk Hovy*

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

Large Language Models (LLMs) have demonstrated significant advancements in various fields, notably in Role-Playing Conversational Agents (RPCAs). However, when confronted with role-specific professional inquiries, LLMs-based RPCAs tend to underperform due to their excessive emphasis on the conversational abilities of characters rather than effectively invoking and integrating relevant expert knowledge. This often results in inaccurate responses. We refer to this phenomenon as the "Knowledge Misalignment" which underscores the limitations of RPCAs in integrating expert knowledge. To mitigate this issue, we have introduced an Anchoring-Guidance Fine-Tuning (AnGFT) Framework into the RPCAs' training process. This involves initially linking the Anchoring-Based System Prompt (ASP) with the LLM's relevant expert domains through diverse prompt construction strategies and supervised fine-tuning (SFT). Following the role-play enriched SFT, the integration of ASP enables LLMs to better associate with relevant expert knowledge, thus enhancing their response capabilities in role-specific expert domains. Moreover, we have developed four comprehensive metrics—helpfulness, thoroughness, credibility, and feasibility—to evaluate the proficiency of RPCAs in responding to professional questions. Our method was tested across four professional fields, and the experimental outcomes suggest that the proposed Anchoring-Guidance Fine-Tuning Framework substantially improves the RPCAs' performance in handling role-specific professional queries, thereby enhancing the agents' response quality while preserving their robust role-playing abilities.

Anchoring-Guidance Fine-Tuning (AnGFT): Elevating Professional Response Quality in Role-Playing Conversational Agents

Persona assignment has become a common strategy for customizing LLM use to particular tasks and contexts. In this study, we explore how evaluation of different nations changes when LLMs are assigned specific nationality personas. We assign 193 different nationality personas (e.g., an American person) to five LLMs and examine how the LLM evaluations (or ``perceptions'') of countries change. We find that all LLM-persona combinations tend to favor Western European nations, though nation-personas push LLM behaviors to focus more on and treat the nation-persona's own region more favorably. Eastern European, Latin American, and African nations are treated more negatively by different nationality personas. We additionally find that evaluations by nation-persona LLMs of other nations correlate with human survey responses but fail to match the values closely. Our study provides insight into how biases and stereotypes are realized within LLMs when adopting different national personas. Our findings underscore the critical need for developing mechanisms to ensure that LLM outputs promote fairness and avoid over-generalization.

Exploring Changes in Nation Perception with Nationality-Assigned Personas in LLMs

This paper focuses on generating speech with the acoustic style that meets users' needs based on their open-domain instructions. To control the style, early work mostly relies on pre-defined rules or templates. The control types and formats are fixed in a closed domain, making it hard to meet diverse needs of users. One solution is to resort to instructions in free text to guide the generation. Current work mainly studies the instructions that clearly specify the acoustic styles, such as low pitch and fast speed. However, the instructions are complex, some even vague and abstract, such as ``Generate a voice of a woman who is heartbroken due to a breakup. It is hard to infer this implicit style by traditional matching-based methods. To address this problem, we propose a new controllable model. It first utilizes multimodal LLMs with knowledge-augmented techniques to infer the desired speech style from the instructions. The powerful language understanding ability of LLMs can help us better elicit the implicit style factors from the instruction. By using these factors as a control condition, we design a diffusion-based generator adept at finely adjusting speech details. That offers higher flexibility to meet complex users' needs. Next, we verify the output speech from three aspects, i.e., consistency of decoding state, mel-spectrogram, and instruction style. This verified feedback can inversely optimize the generator. Extensive experiments are conducted on three popular datasets. The results show the effectiveness and good controllability of our approach.

Eliciting Implicit Acoustic Styles from Open-domain Instructions to Facilitate Fine-grained Controllable Generation of Speech

Large language models (LLMs) trained over extensive corpora risk memorizing sensitive, copyrighted, or toxic content. To address this, we propose \textbf{OBLIVIATE}, a robust unlearning framework that removes targeted data while preserving model utility. The framework follows a structured process: extracting target tokens, building retain sets, and fine-tuning with a tailored loss function comprising three components---masking, distillation, and world fact. Using low-rank adapters (LoRA), it ensures efficiency without compromising unlearning quality. We conduct experiments on multiple datasets, including the Harry Potter series, WMDP, and TOFU, using a comprehensive suite of metrics: \emph{forget quality} (new document-level memorization score), \emph{model utility}, and \emph{fluency}. Results demonstrate its effectiveness in resisting membership inference attacks, minimizing the impact on retained data, and maintaining robustness across diverse scenarios.

OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models

In recent years, Large Language Models (LLMs) have been widely applied to legal tasks. To enhance their understanding of legal texts and improve reasoning accuracy, a promising approach is to incorporate legal theories. One of the most widely adopted theories is the Four-Element Theory (FET), which defines the crime constitution through four elements: Subject, Object, Subjective Aspect, and Objective Aspect. While recent work has explored prompting LLMs to follow FET, our evaluation demonstrates that LLM-generated four-elements are often incomplete and less representative, limiting their effectiveness in legal reasoning. To address these issues, we present JUREX-4E, an expert-annotated four-elements knowledge base covering 155 criminal charges. The annotations follow a progressive hierarchical framework grounded in legal source validity and incorporate diverse interpretive methods to ensure precision and authority. We evaluate JUREX-4E on the Similar Charge Distinction task and apply it to Legal Case Retrieval. Experimental results validate the high quality of JUREX-4E and its substantial impact on downstream legal tasks, underscoring its potential for advancing legal AI applications. The dataset and code are available at: \url{https://anonymous.4open.science/r/JUREX-86B9/}

JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning

Detoxification in large language models (LLMs) remains a significant research challenge. Existing decoding detoxification methods are all based on external constraints, which require additional resource overhead and lose generation fluency. This work innovatively proposes Detoxification with Self-Constrained Decoding (DSCD), a novel method for LLMs detoxification without parameter fine-tuning. DSCD strengthens the inner token distribution of the safety layer while weakening that of hallucination and toxic layer during output generation. This effectively diminishes toxicity and enhances output safety. DSCD offers lightweight, high compatibility, and plug-and-play capabilities, readily integrating with existing detoxification methods for further performance improvement. Extensive experiments on representative open-source LLMs and public datasets validate DSCD’s effectiveness, demonstrating state-of-the-art (SOTA) performance in both detoxification and generation fluency, with superior efficiency compared to existing methods. These results highlight DSCD’s potential as a practical and scalable solution for safer LLM deployments.

DSCD: Large Language Model Detoxification with Self-Constrained Decoding

Detecting depression through users' social media posting history is crucial for enabling timely intervention; however, irrelevant content within these posts negatively impacts detection performance. Thus, it is crucial to extract pertinent content from users' complex posting history. Current methods utilize frozen screening models, which can miss critical information and limit overall performance due to isolated screening and detection processes. To address these limitations, we propose **E2-LPS** **E**nd-to-**E**nd **L**earnable **P**sychiatric Scale Guided Risky Post **S**creening Model) for jointly training our screening model, guided by psychiatric scales, alongside the detection model. We employ a straight-through estimator to enable a learnable end-to-end screening process and avoid the non-differentiability of the screening process. Experimental results show that E2-LPS outperforms several strong baseline methods, and qualitative analysis confirms that it better captures users' mental states than others.

End-to-End Learnable Psychiatric Scale Guided Risky Post Screening for Depression Detection on Social Media

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities such as text coherence and task accuracy. And Prompt-based debiasing methods, only effective for predefined trigger words, fail to address deeply embedded stereotypical associations in model parameters. In this paper, we propose BiasUnlearn, a novel model debiasing framework which achieves targeted debiasing via dual-pathway unlearning mechanisms coordinating stereotype forgetting with anti-stereotype retention, while preventing bias polarity reversal through adversarial forget set and dynamic dataset swapping. We conducted extensive experiments with multiple language models across various evaluation benchmarks. The results show that BiasUnlearn outperforms existing methods in mitigating bias in language models while retaining language modeling capabilities. Further experiments reveal that debiasing weights are transferable across model variants, confirming that bias representations become entrenched during pre-training and persist through fine-tuning phases.

Mitigating Biases in Language Models via Bias Unlearning

Recent advances in large reasoning models (LRMs) have enabled strong multi-step reasoning capabilities. However, existing machine unlearning algorithms are tailored to standard language modeling and fail to address the unique challenges posed by LRMs. In this work, we present the first systematic study of LRM unlearning and reveal that conventional unlearning methods often overlook critical information leakage in reasoning traces, even when final answers are successfully removed. To address this, we propose Reasoning-aware Representation Misdirection for Unlearning (R²MU), a method that suppresses sensitive reasoning traces while preserving the model’s general reasoning ability. Our experiments demonstrate that R²MU significantly reduces reasoning trace leakage and achieves strong performance across both reasoning and safety benchmarks, including WMDP, StrongReject, JBB-Behaviors and WildJailbreak, under state-of-the-art models such as DeepSeek-R1-Distill-LLaMA-8B and DeepSeek-R1-Distill-Qwen-14B. To the best of our knowledge, MU is the first principled approach to both expose and mitigate reasoning trace leakage in LRM unlearning, while preserving reasoning ability.

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills

While densely annotated image captions significantly facilitate the learning of robust vision-language alignment, methodologies for systematically optimizing human annotation efforts remain underexplored. We introduce Chain-of-Talkers (CoTalk), an AI-in-the-loop methodology designed to maximize the number of annotated samples and improve their comprehensiveness under fixed budget constraints (e.g., total human annotation time). The framework is built upon two key insights. First, sequential annotation reduces redundant workload compared to conventional parallel annotation, as subsequent annotators only need to annotate the ``residual''---the missing visual information that previous annotations have not covered. Second, humans process textual input faster by reading while outputting annotations with much higher throughput via talking; thus a multimodal interface enables optimized efficiency. We evaluate our framework from two aspects: intrinsic evaluations that assess the comprehensiveness of semantic units, obtained by parsing detailed captions into object-attribute trees and analyzing their effective connections; extrinsic evaluation measures the practical usage of the annotated captions in facilitating vision-language alignment. Experiments with eight participants show our Chain-of-Talkers (CoTalk) improves annotation speed (0.42 vs. 0.30 units/sec) and retrieval performance (41.13% vs. 40.52%) over the parallel method.

Downloads

Next from EMNLP 2025

Anchoring-Guidance Fine-Tuning (AnGFT): Elevating Professional Response Quality in Role-Playing Conversational Agents

Similar lecture

Pisets: A Robust Speech Recognition System for Lectures and Interviews

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES