United States

Large Language Models (LLMs) are primarily trained on high-resource natural languages, limiting their effectiveness in low-resource settings and in tasks requiring deep logical reasoning. This research investigates the use of a custom logical language as a controlled environment for evaluating LLMs&#39; pattern recognition and problem-solving abilities. We assess their logical accuracy and generalization capabilities by translating a dataset of logical propositions from Lean into this newly created language, which is then used to fine-tune an LLM (e.g GPT-4o). Our experiments analyze the impact of the size of the dataset and the translation methodology on the performance of the model. Our results indicate that preserving logical relationships in translation process significantly boost precision, with accuracy plateauing beyond roughly 20,000 training samples. These insights provide valuable guidelines for optimizing LLM training in formal reasoning tasks and improving performance in various low-resource language applications.

NAACL 2025

Propositional Logic as a Benchmark for Large Language Model Reasoning

translation strategies

logical language

propositional logic

logical reasoning

large language models

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Large Language Models (LLMs) are primarily trained on high-resource natural languages, limiting their effectiveness in low-resource settings and in tasks requiring deep logical reasoning. This research investigates the use of a custom logical language as a controlled environment for evaluating LLMs' pattern recognition and problem-solving abilities. We assess their logical accuracy and generalization capabilities by translating a dataset of logical propositions from Lean into this newly created language, which is then used to fine-tune an LLM (e.g GPT-4o). Our experiments analyze the impact of the size of the dataset and the translation methodology on the performance of the model. Our results indicate that preserving logical relationships in translation process significantly boost precision, with accuracy plateauing beyond roughly 20,000 training samples. These insights provide valuable guidelines for optimizing LLM training in formal reasoning tasks and improving performance in various low-resource language applications.

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

Code Language Models have been trained to generate accurate solutions, typically with no regard for runtime. On the other hand, previous works that explored execution optimisation have observed corresponding drops in functional correctness. To that end, we introduce Code-Optimise, a framework that incorporates both correctness (passed, failed) and runtime (quick, slow) as learning signals via self-generated preference data. Our framework is both lightweight and robust as it dynamically selects solutions to reduce overfitting while avoiding a reliance on larger models for learning signals. Code-Optimise achieves significant improvements in pass@k while decreasing the competitive baseline runtimes by an additional 6% for in-domain data and up to 3% for out-of-domain data. As a by-product, the average length of the generated solutions is reduced by up to 48% on MBPP and 23% on HumanEval, resulting in faster and cheaper inference. The generated data and codebase is open-sourced at https://github.com/huawei-noah/HEBO/tree/Code_Optimise.

Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency

With the success of integrating large language models into the development of conversational systems, many studies have shown the effectiveness of retrieving and augmenting external knowledge for informative responses. While many existing studies agree on the necessity of Retrieval Augmented Generation (RAG), further investigation into the necessity and value of applying RAG to every turn of the conversation is needed. In this study, we propose to investigate the need for each turn of system response to be augmented with external knowledge. In particular, by leveraging human judgements on the binary choice of adaptive augmentation, we develop RAGate, a gating model, which models conversation context and relevant inputs to predict if a conversational system requires RAG for improved responses. We conduct extensive experiments on devising and applying RAGate to conversational models, joined with well-rounded analyses of various conversational scenarios. Our experimental results and analysis indicate the effective application of RAGate in RAG-based conversational systems in identifying if system responses require RAG to generate high-quality responses with high confidence. This study also identifies and shows the correlation between the generation's confidence level and the relevance of the augmented knowledge. We have also released the implementation code and resources in https://github.com/wangxieric/RAGate.

Adaptive Retrieval-Augmented Generation for Conversational Systems

Numerous adversarial defense methods have been proposed to strengthen the robustness of Natural Language Processing (NLP) models against adversarial attacks. However, many of these methods rely on predetermined linguistic knowledge and assume that attackers' synonym candidates are known, which is often unrealistic. In this work, we investigate adversarial training in the embedding space and introduce a Fast Adversarial Training (FAT) method to improve the model robustness without requiring synonym awareness. FAT leverages single-step perturbation generation and effective perturbation initialization based on two key insights: (1) adversarial perturbations generated by single-step and multi-step gradient ascent are similar, and (2) perturbations generated on the same training sample across successive epochs exhibit resemblance. By employing single-step gradient ascent and leveraging historical perturbation information, FAT not only expedites the training process but also efficiently initializes perturbations. Extensive experiments demonstrate that FAT significantly enhances the robustness of popular NLP models under scenarios where synonyms are unknown, outperforming other defense baselines under various character-level and word-level attacks.

Synonym-unaware Fast Adversarial Training against Textual Adversarial Attacks

Current multimodal machine translation (MMT) systems rely on fully supervised data (i.e sentences with their translations and accompanying images), which is costly to collect and prevents the extension of MMT to language pairs with no such data. We propose a method to bypass the need for fully supervised data to train MMT systems, using multimodal English data only. Our method ( ZeroMMT) consists in adapting a strong text-only machine translation (MT) model by training it jointly on two objectives: visually conditioned masked language modelling and the Kullback-Leibler divergence between the original MT and new MMT outputs. We evaluate on standard MMT benchmarks and on CoMMuTE, a contrastive test set designed to evaluate how well models use images to disambiguate translations. ZeroMMT obtains disambiguation results close to state-of-the-art MMT models trained on fully supervised examples. To prove that ZeroMMT generalizes to languages with no fully supervised training data, we extend CoMMuTE to three new languages: Arabic, Russian and Chinese. We also show that we can control the trade-off between disambiguation capabilities and translation fidelity at inference time using classifier-free guidance and without any additional data. Our code, data and trained models are publicly accessible.

Towards Zero-Shot Multimodal Machine Translation

Complex table question answering (TQA) aims to answer questions that require complex reasoning, such as multi-step or multi-category reasoning, over data represented in tabular form. Previous approaches demonstrate notable performance by leveraging either closed-source large language models (LLMs) or fine-tuned open-weight LLMs. However, fine-tuning LLMs requires high-quality training data, which is costly to obtain. The use of closed-source LLMs poses accessibility challenges and leads to reproducibility issues. In this paper, we propose Multi Agent Collaboration with Tool use (MACT), a framework that requires neither fine-tuning nor closed-source models. In MACT, a planning agent and a coding agent that also make use of tools collaborate for TQA. MACT outperforms previous SoTA systems on three out of four benchmarks and performs comparably to the larger and more expensive closed-source model GPT-4 on two benchmarks, even when using only open-weight models without any fine-tuning. Our extensive analyses prove the effectiveness of MACT’s multi-agent collaboration in TQA. We release our code publicly.

Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering

This paper presents ViSP, a high-quality Vietnamese dataset for sentence paraphrasing, consisting of 1.2M original–paraphrase pairs collected from various domains. The dataset was constructed using a hybrid approach that combines automatic paraphrase generation with manual evaluation to ensure high quality. We conducted experiments using methods such as back-translation, EDA, and baseline models like BART and T5, as well as large language models (LLMs), including GPT-4o, Gemini-1.5, Aya, Qwen-2.5, and Meta-Llama-3.1 variants. To the best of our knowledge, this is the first large-scale study on Vietnamese paraphrasing. We hope that our dataset and findings will serve as a valuable foundation for future research and applications in Vietnamese paraphrase tasks. The dataset is available for research purposes at <https://github.com/ngwgsang/ViSP>.

A Large-Scale Benchmark for Vietnamese Sentence Paraphrases

Large language models (LLMs) have shown exceptional performance across various text generation tasks, but remain under-explored in the patent domain, which offers highly structured and precise language. This paper constructs a dataset to investigate the performance of current LLMs in patent claim generation. Our results demonstrate that generating claims based on patent descriptions outperforms previous research relying on abstracts. Interestingly, current patent-specific LLMs perform much worse than state-of-the-art general LLMs, highlighting the necessity for future research on in-domain LLMs. We also find that LLMs can produce high-quality first independent claims, but their performances markedly decrease for subsequent dependent claims. Moreover, fine-tuning can enhance the completeness of inventions' features, conceptual clarity, and feature linkage. Among the tested LLMs, GPT-4 demonstrates the best performance in comprehensive human evaluations by patent experts, with better feature coverage, conceptual clarity, and technical coherence. Despite these capabilities, comprehensive revision and modification are still necessary to pass rigorous patent scrutiny and ensure legal robustness.

Can Large Language Models Generate High-quality Patent Claims?

Existing approaches for low-resource text summarization primarily employ large language models (LLMs) like GPT-3 or GPT-4 at inference time to generate summaries directly; however, such approaches often suffer from inconsistent LLM outputs and are difficult to adapt to domain-specific data in low-resource scenarios. In this work, we propose two novel methods to effectively utilize LLMs for low-resource text summarization: 1) MixSumm, an LLM-based data augmentation regime that synthesizes high-quality documents (short and long) for few-shot text summarization, and 2) PPSL, a prompt-based pseudolabeling strategy for sample-efficient semi-supervised text summarization. Specifically, MixSumm leverages the open-source LLaMA-3-70b-Instruct model to generate new documents by mixing topical information derived from a small seed set, and PPSL leverages the LLaMA-3-70b-Instruct model to generate high-quality pseudo-labels in a semi-supervised learning setup. We evaluate our methods on the TweetSumm, WikiHow, and ArXiv/PubMed datasets and use L-Eval, a LLaMA-3-based evaluation metric, and ROUGE scores to measure the quality of generated summaries. Our experiments on extractive and abstractive summarization show that MixSumm and PPSL achieve competitive ROUGE scores as a fully supervised method with 5% of the labeled data. We release our codebase here: https://github.com/ServiceNow/text-summarization-with-llms/

A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches

This study investigates retrieval-augmented summarization by specifically examining the impact of exemplar summary lengths because previous methods have not considered length constraints. We propose a Diverse Length-aware Maximal Marginal Relevance (DL-MMR) algorithm to better control summary lengths. This algorithm combines the query relevance with diverse target lengths in retrieval-augmented summarization. Unlike previous methods that necessitate exhaustive exemplar-exemplar relevance comparisons using MMR, DL-MMR considers the exemplar target length as well and avoids comparing exemplars to each other, thereby reducing computational cost and conserving memory during the construction of an exemplar pool. Experimental results showed the effectiveness of DL-MMR, which considers length diversity, compared to the original MMR algorithm. DL-MMR additionally showed the effectiveness in memory saving of 781,513 times and computational cost reduction of 500,092 times, while maintaining the same level of informativeness.

Considering Length Diversity in Retrieval-Augmented Summarization

Evaluation of large language models (LLMs) in low-resource languages like Persian has received less attention than in high-resource languages like English. Existing evaluation approaches for Persian LLMs generally lack comprehensive frameworks, limiting their ability to assess models' performance over a wide range of tasks requiring considerable cultural and contextual knowledge, as well as a deeper understanding of Persian literature and style. This paper first aims to fill this gap by providing two new benchmarks, PeKA and PK-BETS, on topics such as history, literature, and cultural knowledge, as well as challenging the present state-of-the-art models' abilities in a variety of Persian language comprehension tasks. These datasets are meant to reduce data contamination while providing an accurate assessment of Persian LLMs. The second aim of this paper is the general evaluation of LLMs across the current Persian benchmarks to provide a comprehensive performance overview. By offering a structured evaluation methodology, we hope to promote the examination of LLMs in the Persian language.

Next from NAACL 2025

Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency

Similar lecture

Logical forms complement probability in understanding language model (and human) performance

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES