China

Large language models (LLMs) have shown promising capabilities in first-order logic (FOL) reasoning, with applications in various areas. However, their effectiveness in complex mathematical reasoning involving multi-step FOL deductions is still under-researched. While LLMs perform competitively on established mathematical reasoning benchmarks, they struggle with multi-step FOL tasks, as demonstrated by Deepseek-Prover-V2-7B&#39;s low accuracy (4.1\%) on our proposed theorem proving dataset. This issue arises from limited exploration of diverse proof strategies and the potential for early reasoning mistakes to undermine entire proofs. To address these issues, we propose DREAM, a self-adaptive solution that enhances the Diversity and REAsonability of LLMs&#39; generation strategies. DREAM incorporates an Axiom-Driven Strategy Diversification mechanism to promote varied strategic outcomes and a Sub-Proposition Error Feedback to help LLMs reflect on and correct their proofs. Our contributions include pioneering advancements in LLMs&#39; mathematical reasoning through FOL theorem proving, introducing a novel inference stage solution that improves performance by 1\% to 5\%, and providing a curated dataset of 447 mathematical theorems in Lean4 format for evaluation.

EMNLP 2025

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving

first-order logic reasoning

mathematical reasoning

large language models

### 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

Large language models (LLMs) have shown promising capabilities in first-order logic (FOL) reasoning, with applications in various areas. However, their effectiveness in complex mathematical reasoning involving multi-step FOL deductions is still under-researched. While LLMs perform competitively on established mathematical reasoning benchmarks, they struggle with multi-step FOL tasks, as demonstrated by Deepseek-Prover-V2-7B's low accuracy (4.1\%) on our proposed theorem proving dataset. This issue arises from limited exploration of diverse proof strategies and the potential for early reasoning mistakes to undermine entire proofs. To address these issues, we propose DREAM, a self-adaptive solution that enhances the Diversity and REAsonability of LLMs' generation strategies. DREAM incorporates an Axiom-Driven Strategy Diversification mechanism to promote varied strategic outcomes and a Sub-Proposition Error Feedback to help LLMs reflect on and correct their proofs. Our contributions include pioneering advancements in LLMs' mathematical reasoning through FOL theorem proving, introducing a novel inference stage solution that improves performance by 1\% to 5\%, and providing a curated dataset of 447 mathematical theorems in Lean4 format for evaluation.

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.

Transformers have become the backbone of modern Large Language Models (LLMs); however, their inference overhead grows linearly with the sequence length, posing challenges for modeling long sequences. In light of this, Mamba has attracted attention for maintaining a constant inference size, with empirical evidence demonstrating that it can match Transformer performance in sequence modeling while significantly reducing computational costs. However, an open question remains: can Mamba always bring savings while achieving performance comparable to Transformers? In this paper, we focus on analyzing the expressive ability of Mamba to perform our defined COPY operation and Chain of Thought (CoT) reasoning. First, inspired by the connection between Mamba and linear attention, we show that constant-sized Mamba may struggle to perform COPY operations while Transformers can handle them more easily. However, when the size of Mamba grows linearly with the input sequence length, it can accurately perform COPY, but in this case, Mamba no longer provides overhead savings. Based on this observation, we further analyze Mamba's ability to tackle CoT tasks, which can be described by the Dynamic Programming (DP) problems. Our findings suggest that to solve arbitrary DP problems, the total cost of Mamba is still comparable to standard Transformers. However, similar to efficient Transformers, when facing DP problems with favorable properties such as locality, Mamba can provide savings in overhead. Our experiments on the copy and CoT tasks further demonstrate Mamba’s limitations compared to Transformers in learning these tasks.

Exploring the Limitations of Mamba in COPY and CoT Reasoning

Promoting positive mental health and well-being, especially in adolescents, is a critical yet underexplored area in natural language processing (NLP). Most existing NLP research focuses on clinical therapy or psychological counseling for the general population, which does not adequately address the preventative and growth-oriented needs of adolescents. In this paper, we introduce DeepWell-Adol, a domain-specific Chinese dialogue corpus grounded in positive psychology and coaching, designed to foster adolescents' positive mental health and well-being. To balance the trade-offs between data quality, quantity, and scenario diversity, the corpus comprises two main components: human expert-written seed data (ensuring professional quality) and its mirrored expansion (automatically generated using a two-stage scenario-based augmentation framework). This approach enables large-scale data creation while maintaining domain relevance and reliability. Comprehensive evaluations demonstrate that the corpus meets general standards for psychological dialogue and emotional support, while also showing superior performance across multiple models in promoting positive psychological processes, character strengths, interpersonal relationships, and healthy behaviors. Moreover, the framework proposed for building and evaluating DeepWell-Adol offers a flexible and scalable method for developing domain-specific datasets. It significantly enhances automation and reduces development costs without compromising professional standards—an essential consideration in sensitive areas like adolescent and elderly mental health.

DeepWell-Adol: A Scalable Expert-Based Dialogue Corpus for Adolescent Positive Mental Health and Wellbeing Promotion

Recent advancements in Large Language Models (LLMs) have driven growing interest in LLM-based agents for complex planning tasks. To avoid costly agent training, many studies adopted memory mechanism that enhances LLM with offline experiences or online trajectory analysis. However, existing works focus on single-granularity memory derived from dynamic environmental interactions, which are inherently constrained by the quality of the collected experiences. This limitation, in turn, constrain the diversity of knowledge and the flexibility of planning. We propose Coarse-to-Fine Grounded Memory (CFGM), a novel framework that grounds coarse-to-fine memories with LLM, thereby fully leverage them for flexible adaptation to diverse scenarios. CFGM grounds environmental information into coarse-grained focus points to guide experience collection in training tasks, followed by grounding of actionable hybrid-grained tips from each experience. At inference, CFGM retrieves task-relevant experiences and tips to support planning. When facing environmental anomalies, the LLM grounds the current situation into fine-grained key information, enabling flexible self-QA reflection and plan correction. Extensive experiments on AlfWorld, Webshop and ScienceWorld demonstrate that CFGM significantly outperforms competitive baselines and comprehensively optimizes memory-enhanced LLM Agent system.

Coarse-to-Fine Grounded Memory for LLM Agent Planning

Large language models (LLMs) have demonstrated strong performance in solving math problems, and there is growing research on evaluating their robustness. Unlike previous studies that create problem variants by adding perturbations to a single problem, this paper focuses on the interaction between problems. Specifically, we combine two original problems with a logical connection to get a new math problem, and measure the LLMs' performance on it to evaluate its compositional generalization, which is an important and essential reasoning capability in human intelligence. The result of experiments that cover 14 different LLMs shows that even when the mathematical essence remains unchanged, a simple form of combination can significantly reduce the performance of LLMs, revealing the limitation of their generalization ability. Additionally, we propose an automated pipeline with 98.2% accuracy to assist in annotating datasets (1 manual, 2 synthetic). The extensive experiments conducted on these datasets further verify the conclusion and obtain some important findings. Finally, we analyze the impact of factors such as difficulty and length on LLMs performance, offering insights for future research.

From A and B to A+B: Can Large Language Models Solve Compositional Math Problems?

Process Reward Models (PRMs) have emerged as a promising solution to address the reasoning mistakes of large language models (LLMs). However, existing PRMs typically output evaluation scores directly, limiting both learning efficiency and evaluation accuracy, which is further exacerbated by the scarcity of annotated data. To address these issues, we propose Reasoning-Driven Process Reward Modeling (R-PRM), which leverages the reasoning ability to improve process-level evaluation. First, we leverage stronger LLMs to generate seed data from limited annotations, effectively activating reasoning capabilities and enabling comprehensive step-by-step evaluation. Second, we explore self-improvement of our PRM through preference optimization, without requiring additional annotated data. Third, we introduce inference-time scaling to fully harness our model's reasoning potential. Extensive experiments demonstrate R-PRM's effectiveness: on ProcessBench and PRMBench, it surpasses strong baselines by 13.9 and 8.5 F1 scores. When applied to guide mathematical reasoning, R-PRM achieves consistent accuracy improvements of over 8.6 points across six challenging datasets. Further analysis reveals that R-PRM exhibits more comprehensive evaluation and robust generalization capabilities, thereby highlighting significant potential.

R-PRM: Reasoning-Driven Process Reward Modeling

Avoiding the propagation of undue (binary) gender inferences and default masculine language remains a key challenge towards inclusive multilingual technologies, particularly when translating into languages with extensive gendered morphology. Gender-neutral translation (GNT) represents a linguistic strategy towards fairer communication across languages. However, research on GNT is limited to a few resources and language pairs. To address this gap, we introduce mGeNTE, an expert-curated resource, and use it to conduct the first systematic multilingual evaluation of inclusive translation with state-of-the-art instruction-following language models (LMs). Experiments on en-es/de/it/el reveal that while models can recognize when neutrality is appropriate, they cannot consistently produce neutral translations, limiting their usability. To probe this behavior, we enrich our evaluation with interpretability analyses that identify task-relevant features and offer initial insights into the internal dynamics of LM-based GNT.

Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTE

Cochrane produces systematic reviews whose abstracts are divided into seven standard sections. However, the plain language summaries (PLS) of Cochrane reviews do not adhere to the same structure, which has prevented researchers from training simplification models on paired abstract and PLS sections. In this work, we devise a two-step method to automatically divide PLS of Cochrane reviews into the same sections in which abstracts are divided. In the first step, we align each sentence in a PLS to a section in the parallel abstract if they cover similar content. In the second step, we classify the remaining sentences into sections based on the content of the PLS and what we learned from the first step. We manually divide 22 PLS into sections to evaluate our method. Upon execution of our method, we obtain the Cochrane-sections dataset, which consists of paired abstract and PLS sections in English for a total of 7.7K Cochrane reviews. Thus, our work yields references for the section-level simplification of biomedical abstracts.

Section-Level Simplification of Biomedical Abstracts

Recently, inference-time reasoning strategies have further improved the accuracy of large language models (LLMs), but their effectiveness on smaller models remains unclear. Based on the observation that conventional approaches often fail to improve performance in this context, we propose \textbf{C}ycle-\textbf{C}onsistency in \textbf{Q}uestion \textbf{A}nswering (CCQA), a novel reasoning method that can be effectively applied to SLMs. Inspired by cycle consistency, CCQA generates a question from each reasoning path and answer, evaluates each by its similarity to the original question, and then selects the candidate solution with the highest similarity score as the final response. Since conventional SLMs struggle to generate accurate questions from their own reasoning paths and answers, we employ a lightweight Flan-T5 model specialized for question generation to support this process efficiently. From the experimental results, it is verified that CCQA consistently outperforms existing state-of-the-art (SOTA) methods across eight models on mathematical and commonsense reasoning benchmarks. Furthermore, our method establishes a new practical baseline for efficient reasoning in SLMs. Source code can be found at \url{https://github.com/ccqaofficial/ccqa_official.git}.

CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs

Text-Centric Visual Question Answering (TEC-VQA) is a critical research area that requires semantic interactions between objects and scene texts. However, most existing TEC-VQA benchmarks focus on high-resource languages like English and Chinese. Although few works expanding multilingual QA pairs in non-text-centric VQA datasets through translation, which encounters a substantial “visual-textual misalignment” problem when applied to TEC-VQA. Moreover, the open-source nature of these benchmarks and the broad sources of training data for MLLMs have inevitably led to benchmark contamination, resulting in unreliable evaluation results. To alleviate this issue, we propose a contamination-free and more challenging TEC-VQA benchmark called Text-Centric Visual Question Answering in Multilingual Chinese Minority Languages(TVQACML), which involves eight languages, including Standard Chinese, Korean, and six minority languages. TVQACML supports a wide range of tasks, such as Text Recognition, Scene Text-Centric VQA, Document-Oriented VQA, Key Information Extraction (KIE), and Handwritten Mathematical Expression Recognition (HMER), featuring 32,000 question-answer pairs across 8,000 images. Extensive experiments on TVQACML across multiple MLLMs demonstrate the effectiveness of evaluating the MLLMs and enhancing multilingual TEC-VQA performance with fine-tuning.

TVQACML: Benchmarking Text-Centric Visual Question Answering in Multilingual Chinese Minority Languages

Structured information extraction from scientific literature is crucial for capturing core concepts and emerging trends in specialized fields. While existing datasets aid model development, most focus on specific publication sections due to domain complexity and the high cost of annotating scientific texts. To address this limitation, we introduces SciNLP—a specialized benchmark for full-text entity and relation extraction in the Natural Language Processing (NLP) domain. The dataset comprises 60 manually annotated full-text NLP publications, covering 7,072 entities and 1,826 relations. Compared to existing research, SciNLP is the first dataset providing full-text annotations of entities and their relationships in the NLP domain. To validate the effectiveness of SciNLP, we conducted comparative experiments with similar datasets and evaluated the performance of state-of-the-art supervised models on this dataset. Results reveal varying extraction capabilities of existing models across academic texts of different lengths. Cross-comparisons with existing dataset show that SciNLP achieves significant performance improvements on certain baseline models. Using models trained on SciNLP, we implemented automatic construction of a fine-grained knowledge graph for the NLP domain. Our KG has an average node degree of 3.2 per entity, indicating rich semantic topological information that enhances downstream applications. The dataset is publicly available at: https://anonymous.4open.science/r/SciNLP-47E5/.

Downloads

Next from EMNLP 2025

Exploring the Limitations of Mamba in COPY and CoT Reasoning

Similar lecture

Automating Mathematical Proof Generation Using Large Language Model Agents and Knowledge Graphs

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES