United States

Reasoning and linguistic skills form the cornerstone of human intelligence, facilitating problem-solving and decision-making. Recent advances in Large Language Models (LLMs) have led to impressive linguistic capabilities and emergent reasoning behaviors, fueling widespread adoption across application domains. However, LLMs still struggle with complex reasoning tasks, highlighting their systemic limitations. In this work, we focus on evaluating whether LLMs have the requisite representations to reason using two foundational relationships: &#39;&#39;equivalence&#39;&#39; and &#39;&#39;inheritance&#39;&#39;. We introduce novel tasks and benchmarks spanning six languages and observe that current SOTA LLMs often produce conflicting answers to the same questions across languages in 17.3-57.5% of cases and violate inheritance constraints in up to 37.2% cases. To enhance consistency across languages, we propose novel &#39;&#39;Compositional Representations&#39;&#39; where tokens are represented as composition of equivalent tokens across languages, with resulting conflict reduction (up to -4.7%) indicating benefits of shared LLM representations.

NAACL 2025

Towards Robust Knowledge Representations in Multilingual LLMs for Equivalence and Inheritance based Consistent Reasoning

multilingual reasoning

multilingual representations

multilingual pre-training

## 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.

Reasoning and linguistic skills form the cornerstone of human intelligence, facilitating problem-solving and decision-making. Recent advances in Large Language Models (LLMs) have led to impressive linguistic capabilities and emergent reasoning behaviors, fueling widespread adoption across application domains. However, LLMs still struggle with complex reasoning tasks, highlighting their systemic limitations. In this work, we focus on evaluating whether LLMs have the requisite representations to reason using two foundational relationships: ''equivalence'' and ''inheritance''. We introduce novel tasks and benchmarks spanning six languages and observe that current SOTA LLMs often produce conflicting answers to the same questions across languages in 17.3-57.5% of cases and violate inheritance constraints in up to 37.2% cases. To enhance consistency across languages, we propose novel ''Compositional Representations'' where tokens are represented as composition of equivalent tokens across languages, with resulting conflict reduction (up to -4.7%) indicating benefits of shared LLM representations.

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) have shown impressive capabilities across diverse settings, but still struggle as the length and complexity of the context increases. To address this challenge, we propose Thinking Recursively and Dynamically (ThReaD). THREAD frames model generation as a thread of execution that, based on the context, can run to completion or dynamically spawn new threads. By spawning, threads can offload work (e.g., thinking, retrieving information) to child threads, which only return tokens needed for the parent thread to do its work. We apply THREAD in the settings of LLM task solving and question answering, where the dynamic threading allows the model to recursively decompose the given task or question into progressively simpler sub-problems that can be solved by separate child threads. We test THREAD, implemented using a few-shot learning approach, on diverse benchmarks for agent tasks and data-grounded question answering. THREAD achieves state-of-the-art performance with GPT-4 and GPT-3.5 on these benchmarks, including ALFWorld, TextCraft, and WebShop, along with two new benchmarks, DataCommons QA and MIMIC-III ICU QA. In addition, THREAD outperforms existing frameworks by 10% to 50% absolute points with smaller models, including Llama-3-8b and CodeLlama-7b.

THREAD: Thinking Deeper with Recursive Spawning

The prevalence of toxic behavior in online gaming communities necessitates robust detection methods to ensure user safety. We introduce GameTox, a novel dataset comprising 53K game chat utterances annotated for toxicity detection through intent classification and slot filling. This dataset captures the complex relationship between user intent and specific linguistic features that contribute to toxic interactions. We extensively analyze the dataset to uncover key insights into the nature of toxic speech in gaming environments. Furthermore, we establish baseline performance metrics using state-of-the-art natural language processing and large language models, demonstrating the dataset's contribution towards enhancing the detection of toxic behavior and revealing the limitations of contemporary models. Our results indicate that leveraging both intent detection and slot filling provides a significantly more granular and context-aware understanding of harmful messages. This dataset serves as a valuable resource to train advanced models that can effectively mitigate toxicity in online gaming and foster healthier digital spaces. Our dataset is publicly available at: https://github.com/shucoll/GameTox.

GameTox: A Comprehensive Dataset and Analysis for Enhanced Toxicity Detection in Online Gaming Communities

Data is the lifeblood of large language models (LLMs). While the quantity of open-source data available for training LLMs is substantial, its integrity often falls short. For instance, the open-source chat version of Yi-1.5-9B scores 5.20 on AlignBench, while the Chinese Alpaca-GPT4 version scores 4.12. This discrepancy makes it challenging for developers to create models that excel in downstream tasks and instruction following. Therefore, it is essential to improve data integrity. Currently, there are two mainstream methods for enhancing data integrity: data filtering and data augmentation. Due to the labor-intensive and time-consuming nature of performing these tasks manually, some of these efforts are now being undertaken by LLMs, owing to their high alignment with human preferences. However, we have found that performing data filtering or data augmentation with LLMs has limited effectiveness in improving data integrity. In this work, we propose FiNE (**F**iltering and **I**mproving **N**oisy data **E**laborately), a method that performs refined filtering and improvement of training data with LLMs. Using the data obtained through our method to train Yi-1.5-9B, the performance gap on AlignBench between our model and the open-source chat version is reduced from 1.08 to 0.35. Additionally, on HalluQA, our model surpasses the open-source chat version by 8.45.

FiNE: Filtering and Improving Noisy Data Elaborately with Large Language Models

The effectiveness of embedding methods is crucial for optimizing text classification performance in Automated Machine Learning (AutoML). However, selecting the most suitable pre-trained model for a given task remains challenging. This study introduces the Corpus-Driven Domain Mapping (CDDM) pipeline, which utilizes a domain-annotated corpus of pre-fine-tuned models from the Hugging Face Model Hub to improve model selection. Integrating these models into AutoML systems significantly boosts classification performance across multiple datasets compared to baseline methods. Despite some domain recognition inaccuracies, results demonstrate CDDM’s potential to enhance model selection, streamline AutoML workflows, and reduce computational costs.

AutoML Meets Hugging Face: Domain-Aware Pretrained Model Selection for Text Classification

Question Answering (QA) and Visual Question Answering (VQA) are well-studied problems in the language and vision domain. One challenging scenario involves multiple sources of information, each of a different modality, where the answer to the question may exist in one or more sources. This scenario contains richer information but is highly complex to handle. In this work, we formulate a novel question-answer generation (QAG) framework in an environment containing multi-source, multimodal information. The answer may belong to any or all sources; therefore, selecting the most prominent answer source or an optimal combination of all sources for a given question is challenging. To address this issue, we propose a question-guided attention mechanism that learns attention across multiple sources and decodes this information for robust and unbiased answer generation. To learn attention within each source, we introduce an explicit alignment between questions and various information sources, which facilitates identifying the most pertinent parts of the source information relative to the question. Scalability in handling diverse questions poses a challenge. We address this by extending our model to a sparse mixture-of-experts (sparse-MoE) framework, enabling it to handle thousands of question types. Experiments on T5 and Flan-T5 using three datasets demonstrate the model's efficacy, supported by ablation studies.

MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering

Open-source large language models (Os-LLMs) propel the democratization of natural language research by giving the flexibility to augment or update model parameters for performance improvement. 
Nevertheless, like proprietary LLMs, Os-LLMs offer poorer performance on low-resource languages (LRLs) than high-resource languages (HRLs), owing to smaller amounts of training data and underrepresented vocabulary. 
On the other hand, continual pre-training (CPT) with large amounts of language-specific data is a costly proposition in terms of data acquisition and computational resources. 
Our goal is to drastically reduce CPT cost.
To that end, we first develop a new algorithm to select a subset of texts from a larger corpus. We show the effectiveness of our technique using very little CPT data. 
In search of further improvement, we design a new algorithm to select tokens to include in the LLM vocabulary.
We experiment with the recent Llama-3 model and nine Indian languages with diverse scripts and extent of resource availability.
For evaluation, we use IndicGenBench, a generation task benchmark dataset for Indic languages. We experiment with various CPT corpora and augmented vocabulary size and offer insights across language families.

Efficient Continual Pre-training of LLMs for Low-resource Languages

This work presents a speech-to-text system for scientists and journalists whish is based on three-component architecture aimed at improving speech recognition accuracy while minimizing errors and hallucinations associated with the Whisper model. The architecture comprises primary recognition using Wav2Vec2, false positive filtering via the Audio Spectrogram Transformer (AST), and final speech recognition through Whisper. The implementation of curriculum learning methods and the utilization of diverse Russian-language speech corpora significantly enhanced the system's effectiveness. Additionally, advanced uncertainty modeling techniques were introduced, contributing to further improvements in transcription quality. The proposed approaches ensure robust transcribing of long audio data across various acoustic conditions compared to WhisperX and usual Whisper.

Pisets: A Robust Speech Recognition System for Lectures and Interviews

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce model outputs contrary to safety alignments. Existing black-box jailbreak methods often rely on model feedback, repeatedly submitting queries with detectable malicious instructions during the attack search process. Although these approaches are effective, the attacks may be intercepted by content moderators during the search process. We propose an improved transfer attack method that guides malicious prompt construction by locally training a mirror model of the target black-box model through benign data distillation. This method offers enhanced stealth, as it does not involve submitting identifiable malicious instructions to the target model during the search phase. Our approach achieved a maximum attack success rate of 92%, or a balanced value of 80% with an average of 1.5 detectable jailbreak queries per sample against GPT-3.5 Turbo on a subset of AdvBench. These results underscore the need for more robust defense mechanisms.

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen instruction-following examples, i.e., fine-tuning attacks. We take a further step to understand fine-tuning attacks in multilingual LLMs. We first discover cross-lingual generalization of fine-tuning attacks: using a few adversarially chosen instruction-following examples in one language, multilingual LLMs can also be easily compromised (e.g., multilingual LLMs fail to refuse harmful prompts in other languages). Motivated by this finding, we hypothesize that safety-related information is language-agnostic and propose a new method termed Safety Information Localization (SIL) to identify the safety-related information in the model parameter space. Through SIL, we validate this hypothesis and find that only changing 20% of weight parameters in fine-tuning attacks can break safety alignment across all languages. Furthermore, we provide evidence to the alternative pathways hypothesis for why freezing safety-related parameters does not prevent fine-tuning attacks, and we demonstrate that our attack vector can still jailbreak LLMs adapted to new languages.

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks

Moderation is essential for maintaining and improving the quality of online discussions. This involves: (1) countering negativity, e.g. hate speech and toxicity, and (2)~promoting positive discourse, e.g. broadening the discussion to involve other users and perspectives. While significant efforts have focused on addressing negativity, driven by an urgency to address such issues, this left moderation promoting positive discourse (henceforth PositiveModeration}) under-studied. With the recent advancements in LLMs, Positive Moderation can potentially be scaled to vast conversations, fostering more thoughtful discussions and bridging the increasing divide in online interactions. We advance the understanding of Positive Moderation by annotating a dataset on 13 moderation properties, e.g. neutrality, clarity and curiosity. We extract instructions from professional moderation guidelines and use them to prompt LLaMA to generate such moderation. This is followed by extensive evaluation showing that (1) annotators rate generated higher than professional moderation, but still slightly prefer professional moderation in pairwise comparison, and (2) LLMs can be used to estimate human evaluation as an efficient alternative.

Downloads

Next from NAACL 2025

THREAD: Thinking Deeper with Recursive Spawning

Similar lecture

A Survey of Multilingual Reasoning in Language Models

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from NAACL 2025

THREAD: Thinking Deeper with Recursive Spawning

Similar lecture

A Survey of Multilingual Reasoning in Language Models

Downloads