United States

Long-context efficiency has recently become a trending topic in serving large language models (LLMs). And mixture of depths (MoD) is proposed as a perfect fit to bring down both latency and memory. In this paper, however, we discover that MoD can barely transform existing LLMs without costly training over an extensive number of tokens. To enable the transformations from any LLMs to MoD ones, we showcase top-k operator in MoD should be promoted to threshold-p operator, and refinement to architecture and data should also be crafted along. All these designs form our method termed MoDification. Through a comprehensive set of experiments covering model scales from 3B to 70B, we exhibit MoDification strikes an excellent balance between efficiency and effectiveness. MoDification can achieve up to ~1.2× speedup in latency and ~1.8× reduction in memory compared to original LLMs especially in long-context applications.

NAACL 2025

MoDification: Mixture of Depths Made Easy

efficient design

long-context efficiency

mixture of depths

## 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

Large language models (LLMs) have presented significant opportunities to enhance various machine learning applications, including graph neural networks (GNNs). By leveraging the vast open-world knowledge within LLMs, we can more effectively interpret and utilize textual data to better characterize heterophilic graphs, where neighboring nodes often have different labels. However, existing approaches for heterophilic graphs overlook the rich textual data associated with nodes, which could unlock deeper insights into their heterophilic contexts. In this work, we explore the potential of LLMs for modeling heterophilic graphs and propose a novel two-stage framework: LLM-enhanced edge discriminator and LLM-guided edge reweighting. In the first stage, we fine-tune the LLM to better identify homophilic and heterophilic edges based on the textual content of their nodes. In the second stage, we adaptively manage message propagation in GNNs for different edge types based on node features, structures, and heterophilic or homophilic characteristics. To cope with the computational demands when deploying LLMs in practical scenarios, we further explore model distillation techniques to fine-tune smaller, more efficient models that maintain competitive performance. Extensive experiments validate the effectiveness of our framework, demonstrating the feasibility of using LLMs to enhance node classification on heterophilic graphs.

Exploring the Potential of Large Language Models for Heterophilic Graphs

Open-domain dialogue systems have seen remarkable advancements with the development of large language models (LLMs). Nonetheless, most existing dialogue systems predominantly focus on brief single-session interactions, neglecting the real-world demands for long-term companionship and personalized interactions with chatbots. Crucial to addressing this real-world need are event summary and persona management, which enable reasoning for appropriate long-term dialogue responses. Recent progress in the human-like cognitive and reasoning capabilities of LLMs suggests that LLM-based agents could significantly enhance automated perception, decision-making, and problem-solving. In response to this potential, we introduce a model-agnostic framework, the Long-term Dialogue Agent (LD-Agent), which incorporates three independently tunable modules dedicated to event perception, persona extraction, and response generation. For the event memory module, long and short-term memory banks are employed to separately focus on historical and ongoing sessions, while a topic-based retrieval mechanism is introduced to enhance the accuracy of memory retrieval. Furthermore, the persona module conducts dynamic persona modeling for both users and agents. The integration of retrieved memories and extracted personas is subsequently fed into the generator to induce appropriate responses. The effectiveness, generality, and cross-domain capabilities of LD-Agent are empirically demonstrated across various illustrative benchmarks, models, and tasks. The code is released at https://github.com/leolee99/LD-Agent.

Hello Again! LLM-powered Personalized Agent for Long-term Dialogue

In-Context Learning (ICL) typically utilizes classification criteria from output probabilities of manually selected label tokens. However, we argue that such token-based classification criteria lead to suboptimal decision boundaries, despite delicate calibrations through translation and constrained rotation applied. To address this problem, we propose Hidden Calibration, which renounces token probabilities and uses the nearest centroid classifier on the LM's last hidden states. In detail, we assign the label of the nearest centroid previously estimated from a calibration set to the test sample as the predicted label. Our experiments on 6 models and 10 classification datasets indicate that Hidden Calibration consistently outperforms current token-based baselines by about 20%~50%, achieving a strong state-of-the-art in ICL. Our further analysis demonstrates that Hidden Calibration finds better classification criteria with less inter-class overlap, and LMs provide linearly separable intra-class clusters with the help of demonstrations, which supports Hidden Calibration and gives new insights into the principle of ICL. Our official code implementation can be found at https://github.com/hc495/Hidden_Calibration.

Token-based Decision Criteria Are Suboptimal in In-context Learning

Counterspeech has emerged as a popular and effective strategy for combating online hate speech, sparking growing research interest in automating its generation using language models. However, the field still lacks standardised evaluation protocols and reliable automated evaluation metrics that align with human judgement. Current automatic evaluation methods, primarily based on similarity metrics, do not effectively capture the complex and independent attributes of counterspeech quality, such as contextual relevance, aggressiveness, or argumentative coherence. This has led to an increased dependency on labor-intensive human evaluations to assess automated counter-speech generation methods. To address these challenges, we introduce `CSEval`, a novel dataset and framework for evaluating counterspeech quality across four dimensions: *contextual-relevance*, *aggressiveness*, *argument-coherence*, and *suitableness*. Furthermore, we propose *Auto-Calibrated COT for Counterspeech Evaluation* (`Auto-CSEval`), a prompt-based method with auto-calibrated chain-of-thoughts (CoT) for scoring counterspeech using large language models. Our experiments show that `Auto-CSEval` outperforms traditional metrics like ROUGE, METEOR, and BertScore in correlating with human judgement, indicating a significant improvement in automated counterspeech evaluation.

CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs

Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. In this paper, we systematically explore the abilities of open LLMs with less than ten billion parameters to handle multilingual machine translation (MT) tasks. We conduct comprehensive evaluations on six popular LLMs and find that models like Gemma2-9B exhibit impressive multilingual translation capabilities. We then introduce the Parallel-First Monolingual-Second (PFMS) data mixing strategy in the continual pretraining stage to further enhance the MT performance and present GemmaX2-28, a 9B model achieving top-tier multilingual translation performance across 28 languages. Specifically, GemmaX2-28 consistently outperforms the state-of-the-art (SOTA) models such as TowerInstruct and X-ALMA and achieves competitive performance with Google Translate and GPT-4-turbo.

Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study

We find that existing instruction-tuned models usually struggle to adhere to a query with multiple intentions, which impairs their performance when the completion of several tasks is demanded by a single command. Hence, this paper teaches models to respond to sequential instructions. Our first attempt stems from a task-driven perspective, manually creating additional intermediate tasks to train multilingual and visual question answering. Next, we develop an automatic and generic process that turns instructions in existing data into diverse and complex task chains. Models that underwent sequential instruction tuning follow a list of instructions better and deliver higher results in coding, maths, and open-ended generation. Moreover, we put forward a new benchmark named SeqEval to evaluate a model's ability to follow all the instructions in a sequence, which further corroborates the benefits of our sequential instruction tuning method.

Fine-Tuning Large Language Models with Sequential Instructions

Large Language Models exhibit impressive reasoning capabilities across diverse tasks, motivating efforts to distill these capabilities into smaller models through generated reasoning data. However, direct training on such synthesized reasoning data may lead to superficial imitation of reasoning process, rather than fostering a genuine integration of reasoning capabilities with underlying knowledge. To address this, we propose TinyThinker, a framework introducing two novel approaches. First, we introduce a three-stage process that incrementally guides the student model through the reasoning process, progressively refining knowledge from coarse to fine granularity. Second, we develop a two-phase training framework comprising an initial reasoning acquisition phase followed by a self-reflection phase utilizing self-generated data. Experiments on commonsense reasoning benchmarks demonstrate that TinyThinker achieves superior performance compared to baselines. Ablation studies further validate the effectiveness of each component in our framework. We expect that TinyThinker can be extended to other knowledge-intensive reasoning tasks, offering an alternative strategy for developing effective reasoning capabilities in smaller language models. Codes are available at https://github.com/shengminp/TinyThinker.

TinyThinker: Distilling Reasoning through Coarse-to-Fine Knowledge Internalization with Self-Reflection

Role-playing agents (RPAs) powered by large language models (LLMs) have been widely utilized in dialogue systems for their capability to deliver personalized interactions. Current evaluations of RPAs mainly focus on personality fidelity, tone imitation, and knowledge consistency, while overlooking emotional fidelity, a key factor that affects user experience. To this end, we propose a benchmark called EmoCharacter to assess emotional fidelity of RPAs in dialogues. EmoCharacter includes two benchmark datasets (single-turn and multi-turn dialogues), three evaluation settings, and six metrics to measure the emotional fidelity between RPAs and the characters they portray. Based on EmoCharacter, we conduct extensive evaluations on RPAs powered by seven widely used LLMs with representative role-playing methods. Our empirical findings reveal that: (1) Contrary to intuition, current role-playing methods often reduce the emotional fidelity of LLMs in dialogues; (2) Enhancing the general capabilities of LLMs does not necessarily improve the emotional fidelity of RPAs; (3) Fine-tuning or In-Context Learning based on real dialogue data can enhance emotional fidelity.

EmoCharacter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues

Document-level relation extraction (DocRE) provides a broad context for extracting one or more relations for each entity pair. Large language models (LLMs) have made great progress in relation extraction tasks. However, one of the main challenges we face is that LLMs have difficulty in multi-label relation prediction tasks. Additionally, another noteworthy challenge and discovery we reveal: the small language models (SLMs) for DocRE tend to classify existing relations as ''no relation'' (NA), while LLMs tend to predict existing relations for all entity pairs. To address these challenges, we propose a novel method that utilizes LLMs as a refiner, employing task distribution and probability fusion. The task distribution we carefully designed aims to distinguish hard and easy tasks, and feed hard tasks to our LLMs-based framework to reevaluate and refine. Further, in order to effectively solve the multi-label relation prediction problem in the refinement process, we propose a probability fusion method, ensuring and enhancing fusion predictions by maintaining a balance between SLMs and LLMs. Extensive experiments on widely-used datasets demonstrate that our method outperforms existing LLMbased methods without fine-tuning by an average of 25.2% F1. Refining SLMs using our method consistently boosts the performance of the SLMs, achieving new state-of-the-art results compared to existing SLMs and LLMs. Our code: https://github.com/Drasick/Drell.

Rethinking the Role of LLMs for Document-level Relation Extraction: a Refiner with Task Distribution and Probability Fusion

Fact-checking pipelines increasingly adopt the Decompose-Then-Verify paradigm, where texts are broken down into smaller claims for individual verification and subsequently combined for a veracity decision. While decomposition is widely-adopted in such pipelines, its effects on final fact-checking performance remain underexplored. Some studies have reported improvements from decompostition, while others have observed performance declines, indicating its inconsistent impact. To date, no comprehensive analysis has been conducted to understand this variability. To address this gap, we present an in-depth analysis that explicitly examines the impact of decomposition on downstream verification performance. Through error case inspection and experiments, we introduce a categorization of decomposition errors and reveal a trade-off between accuracy gains and the noise introduced through decomposition. Our analysis provides new insights into understanding current system's instability and offers guidance for future studies toward improving claim decomposition in fact-checking pipelines.

Downloads

Next from NAACL 2025

Exploring the Potential of Large Language Models for Heterophilic Graphs

Similar lecture

Router-Tuning: A Simple and Effective Approach for Dynamic Depth

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES