United States

A small subset of dimensions within language Transformers&#39; representation spaces emerge as &#39;&#39;outliers&#39;&#39; during pretraining, encoding critical knowledge sparsely. We extend previous findings on emergent outliers to Encoder-Decoder Transformers and instruction-finetuned models, and tackle the problem of distilling a student Transformer from a larger teacher Transformer. Knowledge distillation reduces model size and cost by transferring knowledge from a larger teacher to a smaller student, necessitating a trade-off among representation dimensions. We show that emergent outlier dimensions contribute significantly more to zero-shot performance than non-outlier dimensions. Based on this, we propose the Emergent Outlier Focused Distillation (EOFD) method, which prioritizes critical outlier dimensions in distillation using a weighted MSE loss. We empirically demonstrate that EOFD outperforms state-of-the-art distillation methods and generalizes well across Encoder-only BERT, Decoder-only GPT-2, and Encoder-Decoder T5 architectures.

NAACL 2025

On the Analysis and Distillation of Emergent Outlier Properties in Pre-trained Language Models

layer norm

emergent outlier properties

intervention

distillation

sparsity

pre-training

analysis

language models

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

A small subset of dimensions within language Transformers' representation spaces emerge as ''outliers'' during pretraining, encoding critical knowledge sparsely. We extend previous findings on emergent outliers to Encoder-Decoder Transformers and instruction-finetuned models, and tackle the problem of distilling a student Transformer from a larger teacher Transformer. Knowledge distillation reduces model size and cost by transferring knowledge from a larger teacher to a smaller student, necessitating a trade-off among representation dimensions. We show that emergent outlier dimensions contribute significantly more to zero-shot performance than non-outlier dimensions. Based on this, we propose the Emergent Outlier Focused Distillation (EOFD) method, which prioritizes critical outlier dimensions in distillation using a weighted MSE loss. We empirically demonstrate that EOFD outperforms state-of-the-art distillation methods and generalizes well across Encoder-only BERT, Decoder-only GPT-2, and Encoder-Decoder T5 architectures.

poster

### 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!

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

Large language models (LLMs) can learn vast amounts of knowledge from diverse domains during pre-training. However, long-tail knowledge from specialized domains is often scarce and underrepresented, rarely appearing in the models' memorization. Prior work has shown that in-context learning (ICL) with retriever augmentation can help LLMs better capture long-tail knowledge, reducing their reliance on pre-trained data. Despite these advances, we observe that LLM predictions for long-tail questions remain uncertain to variations in retrieved samples. To take advantage of the uncertainty in ICL for guiding LLM predictions toward correct answers on long-tail samples, we propose a reinforcement learning-based dynamic uncertainty ranking method for retrieval-augmented ICL that accounts for the varying impact of each retrieved sample on LLM predictions. Our approach prioritizes more informative and stable samples while demoting misleading ones, updating rankings based on the feedback from the LLM w.r.t. each retrieved sample. To enhance training efficiency and reduce query costs, we introduce a learnable dynamic ranking threshold, adjusted when the model encounters negative prediction shifts. Experimental results on various question-answering datasets from different domains show that our method outperforms the best baseline by 2.76%, with a notable 5.96% boost in accuracy on long-tail questions that elude zero-shot inference. Our code is available at <https://github.com/Yu-shuyan/uncertian_ranker>.

Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs

Large language models (LLMs) have demonstrated immense potential across various tasks. However, research for exploring and improving the capabilities of LLMs in interpreting graph structures remains limited. To address this gap, we conduct a comprehensive evaluation of prompting current open-source LLMs on graph-to-text generation tasks. Although we explored the optimal prompting strategies and proposed a novel and effective diversity-difficulty-based few-shot sample selection method, we found that the improvements from tuning-free approaches were incremental, as LLMs struggle with planning on complex graphs, particularly those with a larger number of triples. To further improve LLMs in planning with graph sequences and grounding in truth, we introduce a new graph-to-text dataset, PlanGTG, annotated with two sub-tasks: reordering and attribution. Through extensive automatic and human evaluations, we demonstrate significant improvements in the quality of generated text from both few-shot learning and fine-tuning perspectives using the PlanGTG dataset. Our study paves the way for new research directions in graph-to-text generation.

Evaluating and Improving Graph to Text Generation with Large Language Models

Intent classification is crucial for conversational agents (chatbots), and deep learning models perform well in this area. However, little research has been done on the explainability of intent classification due to the absence of suitable benchmark data. Human annotation of explanation signals in text samples is time-consuming and costly. However, from inspection of data on intent classification, we see that, more often than not, the main verb denotes the action, and the direct object indicates the domain of conversation, serving as explanation signals for intent. This observation enables us to hypothesize that the main predicate in the text utterances, along with the arguments of the main predicate, can serve as explanation signals. Leveraging this, we introduce a new technique to automatically augment text samples from intent classification datasets with word-level explanations. We mark main predicates (primarily verbs) and their arguments (dependency relations) as explanation signals in benchmark intent classification datasets ATIS and SNIPS, creating a unique 21k-instance dataset for explainability. Further, we experiment with deep learning and language models. We observe that models that work well for classification do not perform well in explainability metrics like plausibility and faithfulness. We also observe that guiding models to focus on explanation signals from our dataset during training improves the plausibility Token F1 score by 3-4%, improving the model's reasoning.

Main Predicate and Their Arguments as Explanation Signals For Intent Classification

Shame and pride are social emotions expressed across cultures to motivate and regulate people's thoughts, feelings, and behaviors. In this paper, we introduce the first cross-cultural dataset of over 10k shame/pride-related expressions with underlying social expectations from ~5.4K Bollywood and Hollywood movies. We examine *how* and *why* shame and pride are expressed across cultures using a blend of psychology-informed language analysis combined with large language models. We find significant cross-cultural differences in shame and pride expression aligning with known cultural tendencies of the USA and India -- e.g., in Hollywood, shame-expressions predominantly discuss *self* whereas shame is expressed toward *others* in Bollywood. Women are more sanctioned across cultures and for violating similar social expectations.

Social Norms in Cinema: A Cross-Cultural Analysis of Shame, Pride and Prejudice

Cloud-based Large Language Models (LLMs) such as ChatGPT have become increasingly integral to daily operations. Nevertheless, they also introduce privacy concerns: firstly, numerous studies underscore the risks to user privacy posed by jailbreaking cloud-based LLMs; secondly, the LLM service providers have access to all user data, which deters individuals from confidently utilizing such services. To address such concerns, we propose a simple yet effective paradigm, **EmojiPrompt**, to protect user privacy. At its core, EmojiPrompt performs generative transformation, obfuscating private data within prompts with linguistic and non-linguistic elements before submitting them to cloud-based LLMs. We evaluate EmojiPrompt's performance across 8 datasets from various domains. We also propose simulated inference attacks to assess EmojiPrompt's ability to preserve user privacy. The results demonstrate that EmojiPrompt effectively obfuscates user private data, while largely maintaining, or even enhancing, performances compared to the unobfuscated version. Furthermore, EmojiPrompt's atomic-level obfuscation allows it to function exclusively with cloud-based LLMs. For source code, please refer to: https://github.com/agiresearch/EmojiCrypt.

EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs

Medical coding is essential for standardizing clinical data and communication but is often time-consuming and error-prone. Traditional Natural Language Processing (NLP) methods struggle with automating coding due to the large label space, lengthy text inputs, and the absence of supporting evidence annotations that justify code selection. Recent advancements in Generative Artificial Intelligence (AI) offer promising solutions to these challenges. In this work, we introduce MedCodER, an emerging Generative AI framework for automatic medical coding that leverages extraction, retrieval, and re-ranking techniques as core components. MedCodER achieves a micro-F1 score of 0.62 on International Classification of Diseases (ICD) code prediction, significantly outperforming state-of-the-art methods. Additionally, we present a new dataset containing medical records annotated with disease diagnoses, ICD codes, and supporting evidence texts (https://doi.org/10.5281/zenodo.13308316). Ablation tests confirm that MedCodER's performance depends on the integration of each of its aforementioned components, as performance declines when these components are evaluated in isolation.

MedCodER: A Generative AI Assistant for Medical Coding

Large language models (LLMs) have transformed natural language processing but pose significant challenges for real-world deployment. These models necessitate considerable computing resources, which can be costly and frequently unavailable. Model compression techniques such as quantization are often leveraged to alleviate resource demand, but they may have a negative impact on the generation quality. In this study, we explore the integration of 4-bit Post-training Quantization (PTQ) with QLoRA to address these issues. We demonstrate through extensive experiments that this integration outperforms standard PTQ, and in some cases even 16-bit full-parameter fine-tuning on LLMs, validated across proprietary and public datasets with different quantization algorithms. The results demonstrate the efficacy of PTQ-QLoRA integration, offering a viable solution for deploying powerful LLMs in resource-constrained environments without compromising on performance.

Can Post-Training Quantization Benefit from an Additional QLoRA Integration?

Large Language Models (LLMs) face limitations in AI legal and policy applications due to outdated knowledge, hallucinations, and poor reasoning in complex contexts. Retrieval-Augmented Generation (RAG) systems address these issues by incorporating external knowledge, but suffer from retrieval errors, ineffective context integration, and high operational costs. This paper presents the Hybrid Parameter-Adaptive RAG (HyPA-RAG) system, designed for the AI legal domain, with NYC Local Law 144 (LL144) as the test case. HyPA-RAG integrates a query complexity classifier for adaptive parameter tuning, a hybrid retrieval approach combining dense, sparse, and knowledge graph methods, and a comprehensive evaluation framework with tailored question types and metrics. Testing on LL144 demonstrates that HyPA-RAG enhances retrieval accuracy, response fidelity, and contextual precision, offering a robust and adaptable solution for high-stakes legal and policy applications.

HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications

In the digital age, social media platforms like Twitter serve as an extensive repository of public discourse, including instances of sexism. It is important to identify such behavior since radicalized ideologies can lead to real-world violent acts. This project aims to create a deep learning-based tool using GraphSAGE, sentiment analysis and natural language processing (NLP) techniques to capture complex contextual information and relationships within text. The tool will be designed to analyze tweets for sexism detection and classify them into five categories.

Detecting Sexism in Tweets: A Sentiment Analysis and Graph Neural Network Approach

Arabic calligraphy carries rich historical information and meaning. However, the complexity of its artistic elements and the absence of a consistent baseline make text extraction from such works highly challenging. In this paper, we provide an in-depth analysis of the unique obstacles in processing and interpreting these images, including the variability in calligraphic styles, the influence of artistic distortions, and the challenges posed by missing or damaged text elements. We explore potential solutions by leveraging state-of-the-art architectures and deep learning models, including visual language models, to improve text extraction and script completion.

Downloads

Next from NAACL 2025

Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs

Similar lecture

Outlier Dimensions Encode Task Specific Knowledge