United States

Chain-of-thought (CoT) and subsequent methods adopted a deductive paradigm that decomposes the reasoning process, demonstrating remarkable performances across NLP tasks. However, such a paradigm faces the challenge of getting bogged down in low-level semantic details, hindering large language models (LLMs) from correctly understanding, selecting, and compositing conditions. In this work, we present Overarching Prompting (OaP), a simple prompting method that elicits the high-level thinking of LLMs. Specifically, OaP first abstracts the whole problem into a simplified archetype and formulates strategies grounded in concepts and principles, establishing an overarching perspective for guiding reasoning. We conducted experiments with SoTA models, including ChatGPT, InstructGPT, and Llama3-70B-instruct, and received promising performances across tasks including Knowledge QA, Mathematical, and Open-Domain Reasoning. For instance, OaP improved ChatGPT and CoT by 19.0% and 3.1% on MMLU&#39;s College Physics, 8.8% and 2.3% on GSM8k, and 10.3% and 2.5% on StrategyQA, respectively.

NAACL 2025

Forest for the Trees: Overarching Prompting Evokes High-Level Reasoning in Large Language Models

abstraction

prompting

reasoning

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

ACL 2023

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

Chain-of-thought (CoT) and subsequent methods adopted a deductive paradigm that decomposes the reasoning process, demonstrating remarkable performances across NLP tasks. However, such a paradigm faces the challenge of getting bogged down in low-level semantic details, hindering large language models (LLMs) from correctly understanding, selecting, and compositing conditions. In this work, we present Overarching Prompting (OaP), a simple prompting method that elicits the high-level thinking of LLMs. Specifically, OaP first abstracts the whole problem into a simplified archetype and formulates strategies grounded in concepts and principles, establishing an overarching perspective for guiding reasoning. We conducted experiments with SoTA models, including ChatGPT, InstructGPT, and Llama3-70B-instruct, and received promising performances across tasks including Knowledge QA, Mathematical, and Open-Domain Reasoning. For instance, OaP improved ChatGPT and CoT by 19.0% and 3.1% on MMLU's College Physics, 8.8% and 2.3% on GSM8k, and 10.3% and 2.5% on StrategyQA, respectively.

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

As an important fine-grained sentiment analysis task, aspect sentiment triplet extraction (ASTE) aims to identify three elements, i.e., aspect, opinion and sentiment polarity as a triplet. Advanced ASTE researches have mostly explored triplet-wise ability to achieve superior improvement. However, existing models with strong in-house performances may struggle to generalize to the challenging cases with the diverse expression of inter-triplet and intra-triplet elements. To this end, we propose a **M**odel-**A**gnostic **T**raining **O**ptimization (**MATO**) to improve ASTE model inference consistent with expected results facing triplet element diversity. Specifically, we design inter-triplet and intra-triplet metamorphic relations (MRs), and calculate the violation rate (VR) on each element of one triplet through metamorphic testing (MT), indicating the capacity to accommodate the diverse elements. Moreover, we propose an element-wise diversity-aware loss based on the VRs of aspect, opinion and sentiment, which can be jointly trained with existed ASTE models via uncertainty weighing. Conducted on four benchmark datasets and seven ASTE models, experimental results show that our MATO can enhance their diversity capacity, decreasing the average element-wise VRs by 3.28% to 15.36%. Meanwhile, our MATO is comparable to or better than those in terms of F1-score.

MATO: A Model-Agnostic Training Optimization for Aspect Sentiment Triplet Extraction

Mixture-of-Experts (MoE) models have shown remarkable capability in instruction tuning, especially when the number of tasks scales. However, previous methods simply merge all training tasks (e.g. creative writing, coding, and mathematics) and apply fixed sampling weights, without considering the importance of different tasks as the model training state changes. In this way, the most helpful data cannot be effectively distinguished, leading to suboptimal model performance. To reduce the potential redundancies of datasets, we make the first attempt and propose a novel dynamic data mixture for MoE instruction tuning. Specifically, inspired by MoE's token routing preference, we build dataset-level representations and then capture the subtle differences among datasets. Finally, we propose to dynamically adjust the sampling weight of datasets by their inter-redundancies, thus maximizing global performance under a limited training budget. The experimental results on two MoE models demonstrate the effectiveness of our approach on both downstream knowledge & reasoning tasks and open-ended queries.

Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts

Recently, with the development of tool-calling capabilities in large language models (LLMs), these models have demonstrated significant potential for automating electronic design automation (EDA) flows by interacting with EDA tool APIs via EDA scripts. However, considering the limited understanding of EDA tools, LLMs face challenges in practical scenarios where diverse interfaces of EDA tools exist across different platforms. Additionally, EDA flow automation often involves intricate, long-chain tool-calling processes, increasing the likelihood of errors in intermediate steps. Any errors will lead to the instability and failure of EDA flow automation. To address these challenges, we introduce EDAid, a multi-agent collaboration system where multiple agents harboring divergent thoughts converge towards a common goal, ensuring reliable and successful EDA flow automation. Specifically, each agent is controlled by ChipLlama models, which are expert LLMs fine-tuned for EDA flow automation. Our experiments demonstrate the state-of-the-art (SOTA) performance of our ChipLlama models and validate the effectiveness of our EDAid in the automation of complex EDA flows, showcasing superior performance compared to single-agent systems.

Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation

With the expansion of the application of Large Language Models (LLMs), concerns about their safety have grown among researchers. Numerous studies have demonstrated the potential risks of LLMs generating harmful content and have proposed various safety assessment benchmarks to evaluate these risks. However, the evaluation questions in current benchmarks, especially for Chinese, are too straightforward, making them easily rejected by target LLMs, and difficult to update with practical relevance due to their lack of correlation with real-world events. This hinders the effective application of these benchmarks in continuous evaluation tasks. To address these limitations, we propose SafetyQuizzer, a question-generation framework designed to evaluate the safety of LLMs more sustainably in the Chinese context. SafetyQuizzer leverages a finetuned LLM and jailbreaking attack templates to generate subtly offensive questions, which reduces the decline rate. Additionally, by utilizing retrieval-augmented generation, SafetyQuizzer incorporates the latest real-world events into evaluation questions, improving the adaptability of the benchmarks. Our experiments demonstrate that evaluation questions generated by SafetyQuizzer significantly reduce the decline rate compared to other benchmarks while maintaining a comparable attack success rate. Our code is available at https://github.com/zhichao-stone/SafetyQuizzer. Warning: this paper contains examples that may be offensive or upsetting.

SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs

Pre-trained language model (PLM) have achieved great success in text sentiment analysis. However, in practical applications, sentiment is not only conveyed through language but also hidden in other modalities. Therefore, multimodal sentiment analysis (MSA) has attracted increasing research interest. Compared to text sentiment analysis, MSA is challenging since (1) emotions hidden in body movements or vocal timbres eclipse traditional analytical methods, and (2) transferring PLM to MSA task requires huge training parameters. Thus, to solve these issues, we introduce the Mixture of Multimodal Adapters (MMA) into the PLM. Specifically, we first design a mixture-of-multimodal-experts module to capture and fuse emotional movements from different data. Meanwhile, we use a compression parameter for each expert to reduce the training burden. We apply our method to two benchmark datasets and achieve state-of-the-art performance with a tiny trainable parameter count. For example, compared to the current state-of-the-art method, AcFormer, we only need 1/22 of its training parameters amount (130M→6M) to achieve better results.

Mixture of Multimodal Adapters for Sentiment Analysis

Tool-calling has changed Large Language Model (LLM) applications by integrating external tools, significantly enhancing their functionality across diverse tasks. However, this integration also introduces new security vulnerabilities, particularly in the tool scheduling mechanisms of LLM, which have not been extensively studied. To fill this gap, we present ToolCommander, a novel framework designed to exploit vulnerabilities in LLM tool-calling systems through adversarial tool injection. Our framework employs a well-designed two-stage attack strategy. Firstly, it injects malicious tools to collect user queries, then dynamically updates the injected tools based on the stolen information to enhance subsequent attacks. These stages enable ToolCommander to execute privacy theft, launch denial-of-service attacks, and even manipulate business competition by triggering unscheduled tool-calling. Notably, the ASR reaches 91.67% for privacy theft and hits 100% for denial-of-service and unscheduled tool calling in certain cases. Our work demonstrates that these vulnerabilities can lead to severe consequences beyond simple misuse of tool-calling systems, underscoring the urgent need for robust defensive strategies to secure LLM Tool-calling systems.

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection

Recent studies have highlighted the effectiveness of tensor decomposition methods in the Temporal Knowledge Graphs Embedding (TKGE) task. However, we found that inherent heterogeneity among factor tensors in tensor decomposition significantly hinders the tensor fusion process and further limits the performance of link prediction. To overcome this limitation, we introduce a novel method that maps factor tensors onto a unified smooth Lie group manifold to make the distribution of factor tensors approximating homogeneous in tensor decomposition. We provide the theoretical proof of our motivation that homogeneous tensors are more effective than heterogeneous tensors in tensor fusion and approximating the target for tensor decomposition based TKGE methods. The proposed method can be directly integrated into existing tensor decomposition based TKGE methods without introducing extra parameters. Extensive experiments demonstrate the effectiveness of our method in mitigating the heterogeneity and in enhancing the tensor decomposition based TKGE models.

Mitigating Heterogeneity among Factor Tensors via Lie Group Manifolds for Tensor Decomposition Based Temporal Knowledge Graph Embedding

Document retrieval plays a crucial role in numerous question-answering systems, yet research has concentrated on the general knowledge domain and resource-rich languages like English. In contrast, it remains largely underexplored in low-resource languages and cross-lingual scenarios within specialized domain knowledge such as legal. We present a novel dataset designed for cross-lingual retrieval between Vietnamese and English, which not only covers the general domain but also extends to the legal field. Additionally, we propose auxiliary loss function and symmetrical training strategy that significantly enhance the performance of state-of-the-art models on these retrieval tasks. Our contributions offer a significant resource and methodology aimed at improving cross-lingual retrieval in both legal and general QA settings, facilitating further advancements in document retrieval research across multiple languages and a broader spectrum of specialized domains. All the resources related to our work can be accessed at <huggingface.co/datasets/bkai-foundation-models/crosslingual>.

Improving Vietnamese-English Cross-Lingual Retrieval for Legal and General Domains

In this paper, we explore using Large Language Models (LLMs) for rumor detection on social media. It involves assessing the veracity of claims on social media based on social context (e.g., comments, propagation patterns). LLMs, despite their impressive capabilities in text-based reasoning tasks, struggle to achieve promising rumor detection performance when facing long structured social contexts. Our preliminary analysis shows that large-scale contexts hinder LLMs' reasoning abilities, while moderate contexts perform better for LLMs, highlighting the need for refined contexts. Accordingly, we propose a semantic-propagation collaboration-base framework that integrates small language models (e.g., graph attention network) with LLMs for effective rumor detection. It models contexts by enabling text semantic and propagation patterns to collaborate through graph attention mechanisms, and reconstruct the context by aggregating attention values during inference. Also, a cluster-based unsupervised method to refine context is proposed for generalization. Extensive experiments demonstrate the effectiveness of proposed methods in rumor detection. This work bridges the gap for LLMs in facing long, structured data and offers a novel solution for rumor detection on social media.

Exploring Large Language Models for Effective Rumor Detection on Social Media

While Large Language Models (LLMs) have showcased remarkable proficiency in reasoning, there is still a concern about hallucinations and unreliable reasoning issues due to semantic associations and superficial logical chains. To evaluate the extent to which LLMs perform robust reasoning instead of relying on superficial logical chains, we propose a new evaluation dataset, the Concept-Reversed Winograd Schema Challenge (CR-WSC), based on the famous Winograd Schema Challenge (WSC) dataset. By simply reversing the concepts to those that are more associated with the wrong answer, we find that the performance of LLMs drops significantly despite the rationale of reasoning remaining the same. Furthermore, we propose Abstraction-of-Thought (AoT), a novel prompt method for recovering adversarial cases to normal cases using conceptual abstraction to improve LLMs' robustness and consistency in reasoning, as demonstrated by experiments on CR-WSC.

Downloads

Next from NAACL 2025

MATO: A Model-Agnostic Training Optimization for Aspect Sentiment Triplet Extraction

Similar lecture

Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters