United States

In this paper, we present HALLUCANA, a canary lookahead to detect and correct factual hallucinations of Large Language Models (LLMs) in long-form generation. HALLUCANA detects and intervenes as soon as traces of hallucination emerge, during and even before generation. To support timely detection, we exploit the internal factuality representation in the LLM hidden space, where we investigate various proxies to the LLMs’ factuality self-assessment, and discuss its relation to the models’ context familiarity from their pre-training. On biography generation, our method improves generation quality by up to 2.5x, while consuming over 6 times less compute.

NAACL 2025

HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead

lookahead

long-form generation

hallucination

## 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*

EMNLP 2025

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

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

In this paper, we propose a system designed to process and interpret vague, open-ended, and multi-line complex natural language queries, transforming them into coherent, actionable data stories. Our system's modular architecture comprises five components—Question Generation, Answer Generation, NLG/Chart Generation, Chart2Text, and Story Representation—each utilizing LLMs to transform data into human-readable narratives and visualizations. Unlike prior art, our system uniquely addresses the ambiguity of vague, multi-line queries, setting a new benchmark in data storytelling by tackling complexities no existing system comprehensively handles. Our system is cost-effective which uses open-source models without extra training, and emphasizes transparency by showcasing end-to-end processing and intermediate outputs. This enhances explainability, builds user trust, and clarifies the data story generation process.

Goal-Driven Data Story, Narrations and Explanations

Many endangered languages are at risk of extinction due to barriers in communication and generational gaps that hinder their preservation. A cause for languages becoming endangered is the lack of language educational tools and artificial intelligence (AI) models for these low-resource languages. To address this, we propose the ATAIGI learning app designed with AI-powered models leveraging multimodal generative techniques. Our app offers users a comprehensive learning experience by providing translated phrases and definitions, example sentences, illustrative images, romanized pronunciation, and audio speech to accelerate language learning. ATAIGI is built on five AI models that are rigorously benchmarked individually, with our Transliteration Model achieving state-of-the-art results for Taiwanese Hokkien transliteration. ATAIGI is available for all to learn the endangered language of Taiwanese Hokkien, an endangered language spoken in Taiwan. A human evaluation conducted demonstrates the effectiveness of ATAIGI in improving language proficiency and cultural understanding, supporting its potential for the preservation and education of endangered languages like the Taiwanese Hokkien.

ATAIGI: An AI-Powered Multimodal Learning App Leveraging Generative Models for Low-Resource Taiwanese Hokkien

The rapid proliferation of large language models (LLMs) in natural language processing (NLP) has created a critical need for techniques that enable efficient deployment on memory-constrained devices without compromising performance. We present a method to prune LLMs that selectively prunes model blocks based on an importance score and replaces them with a low-parameter replacement strategy. Specifically, we propose a principled metric to replace each pruned block using a weight-sharing mechanism that leverages unpruned counterparts from the model and block-specific low-rank adapters. Furthermore, we facilitate the learning of these replacement blocks with output feature normalization and an adapter initialization scheme built on low-rank SVD reconstructions. Empirical evaluations demonstrate substantial performance gains over existing methods, achieving state-of-the-art performance on 5/6 benchmarks for a compression rate of 30% and 6/6 benchmarks for a compression rate of 40%. We also demonstrate that our approach can extend smaller models, boosting performance on 6/6 benchmarks using only ~0.3% tokens of extended training with minimal additional parameter costs.

FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing

As concern for privacy rights has grown and the size of language model training datasets has expanded, research into machine unlearning for large language models (LLMs) has become crucial. Before the era of LLMs, research on machine unlearning mainly focused on classification tasks in small parameter models. However, as parameter sizes have grown and unlearning targets have become more complex, unlearning has become more challenging, especially in scenarios involving generation instead of classification, as the output space of such models is significantly larger and more diverse. Existing methods based on gradient ascent and its variants often struggle with balancing forget quality and model utility, leading to either over unlearning or partial unlearning. To address this challenge, we propose Reverse KL-Divergence based Knowledge Distillation for Unlearning (RKLU), a novel unlearning method for LLMs. RKLU focuses on precisely unlearning the components of the token distribution related to the unlearning target, allowing us to achieve significant forget quality while maintaining model utility in our experiments.

Balancing Forget Quality and Model Utility: A Reverse KL-Divergence Knowledge Distillation Approach for Better Unlearning in LLMs

Low-resource relation extraction aims to identify semantic relationships between entities using scarce labeled data. Recent studies exploit large language models to recognize relations based on retrieved examplars, yielding promising results. However, the reliability of predictions from these methods is constrained by the presence of irrelevant context within demonstrations and the inherent flaws of large language models in producing undesired outputs. Inspired by the precision and generalization of abstract logic, in this paper, we propose distilling logical rules to uniformly represent task knowledge sourced from distinct origins and facilitate deductive reasoning. We develop a collaborative annotating framework that iteratively integrates high-confidence predictions of rule-enhanced relation extractors with varying scales, efficiently obtaining reliable pseudo annotations from massive unlabeled samples without human supervision. Experiments under two inference settings show that our approach achieves new state-of-the-art performance on benchmark datasets in few-shot scenarios.

Improving Data Annotation for Low-Resource Relation Extraction with Logical Rule-Augmented Collaborative Language Models

Flow matching offers a robust and stable approach to training diffusion models. However, directly applying flow matching to neural vocoders can result in subpar audio quality. In this work, we present WaveFM, a reparameterized flow matching model for mel-spectrogram conditioned speech synthesis, designed to enhance both sample quality and generation speed for diffusion vocoders. Since mel-spectrograms represent the energy distribution of waveforms, WaveFM adopts a mel-conditioned prior distribution instead of a standard Gaussian prior to minimize unnecessary transportation costs during synthesis. Moreover, while most diffusion vocoders rely on a single loss function, we argue that incorporating auxiliary losses, including a refined multi-resolution STFT loss, can further improve audio quality. To speed up inference without degrading sample quality significantly, we introduce a tailored consistency distillation method for WaveFM. Experiment results demonstrate that our model achieves superior performance in both quality and efficiency compared to previous diffusion vocoders, while enabling waveform generation in a single inference step.

WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching

Books, while often rich in cultural insights, can also mirror societal biases of their eras—biases that Large Language Models (LLMs) may learn and perpetuate during training. We introduce a novel method to trace and quantify these biases using fine-tuned LLMs. We develop BookPAGE, a corpus comprising 593 fictional books across seven decades (1950-2019), to track bias evolution. By fine-tuning LLMs on books from each decade and using targeted prompts, we examine shifts in biases related to gender, sexual orientation, race, and religion. Our findings indicate that LLMs trained on decade-specific books manifest biases reflective of their times, with both gradual trends and notable shifts. For example, model responses showed a progressive increase in the portrayal of women in leadership roles (from 8% to 22%) from the 1950s to 2010s, with a significant uptick in the 1990s (from 4% to 12%), possibly aligning with third-wave feminism. Same-sex relationship references increased markedly from the 1980s to 2000s (from 0% to 10%), mirroring growing LGBTQ+ visibility. Concerningly, negative portrayals of Islam rose sharply in the 2000s (26% to 38%), likely reflecting post-9/11 sentiments. Importantly, we demonstrate that these biases stem mainly from the books' content and not the models' architecture or initial training. Our study offers a new perspective on societal bias trends by bridging AI, literary studies, and social science research.

Fine-Tuned LLMs are ''Time Capsules'' for Tracking Societal Bias Through Books

Aligning language models (LMs) with curated human feedback is critical to control their behaviors in real-world applications. Several recent policy optimization methods, such as DPO and SLiC, serve as promising alternatives to the traditional Reinforcement Learning from Human Feedback (RLHF) approach. In practice, human feedback often comes in a format of a ranked list over multiple responses to amortize the cost of reading prompt. Multiple responses can also be ranked by reward models or AI feedback. There lacks such a thorough study on directly fitting upon a list of responses. In this work, we formulate the LM alignment as a listwise ranking problem and describe the LiPO framework, where the policy can potentially learn more effectively from a ranked list of plausible responses given the prompt. This view draws an explicit connection to Learning-to-Rank (LTR), where most existing preference optimization work can be mapped to existing ranking objectives. Following this connection, we provide an examination of ranking objectives that are not well studied for LM alignment, with DPO and SLiC as special cases when list size is two. In particular, we highlight a specific method, LiPO-λ, which leverages a state-of-the-art listwise ranking objective and weights each preference pair in a more advanced manner. We show that LiPO-λ can outperform DPO variants and SLiC by a clear margin on several preference alignment tasks with both curated and real rankwise preference data.

LiPO: Listwise Preference Optimization through Learning-to-Rank

Alignment of large language models (LLMs) with human values and preferences, often achieved through fine-tuning based on human feedback, is essential for ensuring safe and responsible AI behaviors. However, the process typically requires substantial data and computation resources. Recent studies have revealed that alignment might be attainable at lower costs through simpler methods, such as in-context learning. This leads to the question: Is alignment predominantly superficial? In this paper, we delve into this question and provide a quantitative analysis. We formalize the concept of superficial knowledge, defining it as knowledge that can be acquired through easily token restyling, without affecting the model’s ability to capture underlying causal relationships between tokens. We propose a method to extract and isolate those superficial knowledge from aligned models, focusing on the shallow modifications to the final token selection process. By comparing models augmented only with superficial knowledge to fully aligned models, we quantify the superficial portion of alignment. Our findings reveal that while superficial knowledge constitutes a significant portion of alignment, particularly in safety and detoxification tasks, it is not the whole story. Tasks requiring reasoning and contextual understanding still rely on deeper knowledge. Additionally, we demonstrate two practical advantages of isolated superficial knowledge: (1) it can be transferred between models, enabling efficient offsite alignment of larger models using extracted superficial knowledge from smaller models, and (2) it is recoverable, allowing for the restoration of alignment in compromised models without sacrificing performance.

Extracting and Understanding the Superficial Knowledge in Alignment

Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i) Limited controllability—users have minimal influence over the downstream task, as they can only modify input images, while the training of VLMs is often out of reach for most researchers. (ii) Lack of explainability—it is difficult to trace VLM errors to specific causes, such as failures in visual encoding or reasoning. We propose TextFlow, addressing aforementioned issues with two stages: (i) Vision Textualizer—which generates textual representations from flowchart images; and (ii) Textual Reasoner—which performs question-answering based on the text representations. TextFlow offers three key advantages: (i) users can select the type of text representations (e.g., Graphviz, Mermaid, PlantUML), or further convert them into executable graph object to call tools, enhancing performance and controllability; (ii) it improves explainability by helping to attribute errors more clearly to visual or textual processing components; and (iii) it promotes the modularization of the solution, such as allowing advanced LLMs to be used in the reasoner stage when VLMs underperform in end-to-end fashion. Experiments on the FlowVQA and FlowLearn benchmarks demonstrate TextFlow's state-of-the-art performance as well as its robustness. All code and data are publicly available.

Downloads

Next from NAACL 2025

Goal-Driven Data Story, Narrations and Explanations

Similar lecture

Simple Factuality Probes Detect Hallucinations in Long-Form Natural Language Generation