Austria

Large language model (LLM) based agents have shown great potential in following human instructions and automatically completing various tasks. To complete a task, the agent needs to decompose it into easily executed steps by planning. Existing studies mainly conduct the planning by inferring what steps should be executed next starting from the agent&#39;s initial state. However, this forward reasoning paradigm doesn&#39;t work well for complex tasks. We propose to study this issue in Minecraft, a virtual environment that simulates complex tasks based on real-world scenarios. We believe that the failure of forward reasoning is caused by the big perception gap between the agent&#39;s initial state and task goal. To this end, we leverage backward reasoning and make the planning starting from the terminal state, which can directly achieve the task goal in one step. Specifically, we design a backward reasoning based agent (BAR). It is equipped with a recursive goal decomposition module, a state consistency maintaining module and a stage memory module to make robust, consistent, and efficient planning starting from the terminal state. Experimental results demonstrate the superiority of BAR over existing methods and the effectiveness of proposed modules.

ACL 2025

BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks

inference methods

applications

prompting

logical reasoning

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Large language model (LLM) based agents have shown great potential in following human instructions and automatically completing various tasks. To complete a task, the agent needs to decompose it into easily executed steps by planning. Existing studies mainly conduct the planning by inferring what steps should be executed next starting from the agent's initial state. However, this forward reasoning paradigm doesn't work well for complex tasks. We propose to study this issue in Minecraft, a virtual environment that simulates complex tasks based on real-world scenarios. We believe that the failure of forward reasoning is caused by the big perception gap between the agent's initial state and task goal. To this end, we leverage backward reasoning and make the planning starting from the terminal state, which can directly achieve the task goal in one step. Specifically, we design a backward reasoning based agent (BAR). It is equipped with a recursive goal decomposition module, a state consistency maintaining module and a stage memory module to make robust, consistent, and efficient planning starting from the terminal state. Experimental results demonstrate the superiority of BAR over existing methods and the effectiveness of proposed modules.

poster

### 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**. 

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

While multilingual large language models generally perform adequately, and sometimes even rival English performance on high-resource languages (HRLs), they often significantly underperform on low-resource languages (LRLs). Among several prompting strategies aiming at bridging the gap, multilingual in-context learning (ICL) has been particularly effective when demonstration in target languages is unavailable. However, there lacks a systematic understanding when and why it works well.

In this work, we systematically analyze multilingual ICL, using demonstrations in HRLs to enhance cross-lingual transfer. We show that demonstrations in mixed HRLs consistently outperform English-only ones across the board, particularly for tasks written in LRLs. Surprisingly, our ablation study show that the presence of irrelevant non-English sentences in the prompt yields measurable gains, suggesting the effectiveness of multilingual exposure itself. Our results highlight the potential of strategically leveraging multilingual resources to bridge the performance gap for underrepresented languages.

Blessing of Multilinguality: A Systematic Analysis of Multilingual In-Context Learning

Personalized large language models (LLMs) have attracted great attention in many applications, such as emotional support and role-playing. However, existing works primarily focus on modeling explicit character profiles, while ignoring the underlying personality traits that truly shape behaviors and decision-making, hampering the development of more anthropomorphic and psychologically-grounded AI systems. In this paper, we explore the modeling of Big Five personality traits, which is the most widely used trait theory in psychology, and propose P-React, a mixture of experts (MoE)-based personalized LLM. Particularly, we integrate a Personality Specialization Loss (PSL) to better capture individual trait expressions, providing a more nuanced and psychologically grounded personality simulacrum. To facilitate research in this field, we curate OCEAN-Chat, a high-quality, human-verified dataset designed to train LLMs in expressing personality traits across diverse topics. Extensive experiments demonstrate the effectiveness of P-React in maintaining consistent and real personality.

P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts

While Vision-Language Models (VLMs) have shown remarkable abilities, they invariably generate flawed responses. Self-correction that instructs models to refine their outputs presents a promising solution to this issue. Previous studies have mainly concentrated on Large Language Models (LLMs), while the self-correction abilities of VLMs, particularly concerning both visual and linguistic information, remain largely unexamined. This study investigates the self-correction capabilities of VLMs during both inference and fine-tuning stages. We introduce a Self-Correction Learning (SCL) approach that enables VLMs to learn from their self-generated self-correction data through Direct Preference Optimization (DPO) without relying on external feedback, facilitating self-improvement. Experimental results demonstrate that although VLMs struggle to self-correct effectively during iterative inference without additional fine-tuning and external feedback, they can enhance their performance and avoid previous mistakes through preference fine-tuning when their generated self-correction data are categorized into preferred and disfavored samples. This study emphasizes that self-correction is not merely a refinement process; rather, it should enhance models' reasoning ability through additional training, enabling them to generate high-quality responses directly without further refinement.

Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks

Self-improving large language models (LLMs) -- i.e., to improve the performance of an LLM by fine-tuning it with synthetic data generated by itself -- is a promising way to advance the capabilities of LLMs while avoiding extensive supervision. Existing approaches to self-improvement often rely on external supervision signals in the form of seed data and/or assistance from third-party models. This paper presents Crescent -- a simple yet effective framework for generating high-quality synthetic question-answer data in a fully autonomous manner. Crescent first elicits the LLM to generate raw questions via a bait prompt, then diversifies these questions leveraging a rejection sampling-based self-deduplication, and finally feeds the questions to the LLM and collects the corresponding answers by means of majority voting. We show that Crescent sheds light on the potential of true self-improvement with zero external supervision signals for math reasoning; in particular, Crescent-generated question-answer pairs suffice to (i) improve the reasoning capabilities of an LLM while preserving its general performance (especially in the 0-shot setting); and (ii) distill LLM knowledge to weaker models more effectively than existing methods based on seed-dataset augmentation.

The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?

Existing multimodal sentiment analysis (MSA) methods have achieved significant success, leveraging cross-modal large-scale models (LLMs) and extensive pre-training data. However, these methods struggle to handle MSA tasks in low-resource languages. While multilingual LLMs enable cross-lingual transfer, they are limited to textual data and cannot address multimodal scenarios. To achieve MSA in low-resource languages, we propose a novel transfer learning framework named Language Family Disentanglement and Rethinking Transfer (LFD-RT). During pre-training, we establish cross-lingual and cross-modal alignments, followed by a language family disentanglement module that enhances the sharing of language universals within families while reducing noise from cross-family alignments. We propose a rethinking strategy for unsupervised fine-tuning that adapts the pre-trained model to MSA tasks in low-resource languages. Experimental results demonstrate the superiority of our method and its strong language-transfer capability on target low-resource languages. We commit to making our code and data publicly available, and the access link will be provided here.

Cross-lingual Multimodal Sentiment Analysis for Low-Resource Languages via Language Family Disentanglement and Rethinking Transfer

Although multi-agent systems based on large language models show strong capabilities on multiple tasks, they are still limited by high computational overhead, information loss, and robustness. Inspired by ResNet’s residual learning, we propose Residual Mixture-of-Agents (RMoA), integrating residual connections to optimize efficiency and reliability. To maximize information utilization from model responses while minimizing computational costs, we innovatively design an embedding-based diversity selection mechanism that greedily selects responses via vector similarity. Furthermore, to mitigate iterative information degradation, we introduce a Residual Extraction Agent to preserve cross-layer incremental information by capturing inter-layer response differences, coupled with a Residual Aggregation Agent for hierarchical information integration. Additionally, we propose an adaptive termination mechanism that dynamically halts processing based on residual convergence, further improving inference efficiency. RMoA achieves state-of-the-art performance on the benchmarks of across alignment, mathematical reasoning, code generation, and multitasking understanding, while significantly reducing computational overhead. Code is available at https://anonymous.4open.science/r/RMoA-E3D7.

RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation

The improvement of LLMs’ instruction-following capabilities depends critically on the availability of high-quality instruction-response pairs. While existing automatic data synthetic methods alleviate the burden of manual curation, they often rely heavily on either the quality of seed data or strong assumptions about the structure and content of web documents. To tackle these challenges, we propose Web Reconstruction (WebR), a fully automated framework for synthesizing high-quality instruction-tuning (IT) data directly from raw web documents with minimal assumptions. Leveraging the inherent diversity of raw web content, we conceptualize web reconstruction as an instruction-tuning data synthesis task via a novel dual-perspective paradigm—Web as Instruction and Web as Response—where each web document is designated as either the input or output role to trigger the reconstruction process. Comprehensive experiments show that datasets generated by WebR outperform state-of-the-art baselines by up to 16.65% across four instruction-following benchmarks. Notably, WebR demonstrates superior compatibility, data efficiency, and scalability, enabling enhanced domain adaptation with minimal effort.

Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction

Reinforcement Learning from Human Feedback (RLHF) has been shown to effectively align large language models (LLMs) with human knowledge. However, the lack of human preference labels remains a significant bottleneck when applying RLHF to a downstream domain. Humans in RLHF play a critical role in injecting reasoning preferences into LLM, and we assume the reasoning process underlying human assessments may potentially be replaced by reasoning pathways derived from Knowledge Graphs (KGs). Inspired by this assumption, we propose Reinforcement Learning from Knowledge Graph Feedback (RLKGF), a novel method that leverages KG semantics and structure to derive RL rewards in the absence of manual annotations. Unlike Reinforcement Learning from AI Feedback (RLAIF), RLKGF directly integrates human priors encoded in KGs as the reward model, aligning LLM responses with expert knowledge without additional preference labeling or reward model training. RLKGF structures context-relevant facts into knowledge subgraphs and defines rewards by simulating information flow across semantic and logical connections between question and candidate response entities. Experiments on three public and one private medical dialogue dataset demonstrate that RLKGF significantly outperforms the competitive RLAIF in improving LLM diagnostic accuracy. The code is available at \url{https://github.com/YanPioneer/RLKGF}.

RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotations

Recently, O1-like models have emerged as representative examples, illustrating the effectiveness of long chain-of-thought (CoT) in reasoning tasks such as math and coding tasks. In this paper, we introduce DRT, an attempt to bring the success of long CoT to neural machine translation (MT). Specifically, in view of the literature books that might involve similes and metaphors, translating these texts to a target language is very difficult in practice due to cultural differences. In such cases, literal translation often fails to convey the intended meaning effectively. Even for professional human translators, considerable thought must be given to preserving semantics throughout the translation process. To simulate LLMs' long thought ability in MT, we first mine sentences containing similes or metaphors from existing literature books, and then develop a multi-agent framework to translate these sentences via long thought. In the multi-agent framework, a translator is used to iteratively translate the source sentence under the suggestions provided by an advisor. To ensure the effectiveness of the long thoughts, an evaluator is also employed to quantify the translation quality in each round. In this way, we collect tens of thousands of long-thought MT data, which is used to train our DRT. Using Qwen2.5 and LLama-3.1 as the backbones, DRT models can learn the thought process during machine translation, and outperform vanilla LLMs as well as LLMs which are simply fine-tuning on the paired sentences without long thought, showing its effectiveness.

DRT: Deep Reasoning Translation via Long Chain-of-Thought

Indigenous languages remain largely invisible in commercial language identification systems—a stark reality exemplified by Google Translate's LangID tool, which supports 109 languages but excludes all 150 Indigenous languages of North America. This technological marginalization is particularly acute for Alaska's 20 Native languages, all of which face endangerment despite their rich linguistic heritage. We present GenAlaskan, a framework demonstrating how both large language models and specialized classifiers can effectively identify these languages with minimal data. Working closely with Native Alaskan community members, we created Akutaq-2k, a carefully curated dataset of 2000 sentences spanning all 20 languages—named after the traditional Yup'ik dessert symbolizing the blending of diverse elements. We design few-shot learning on proprietary and open-source LLMs, achieving nearly 100% accuracy with just 40 examples per language. While initial zero-shot attempts showed limited success, our systematic attention head pruning revealed critical architectural components for accurate language differentiation, providing insights into model decision-making for low-resource languages. Our results challenge the notion that effective Indigenous language identification requires massive resources or corporate infrastructure, demonstrating that targeted technological interventions can drive meaningful progress in preserving endangered languages in the digital age.

Downloads

Next from ACL 2025

Blessing of Multilinguality: A Systematic Analysis of Multilingual In-Context Learning

Similar lecture

Fill in the Blank: Exploring and Enhancing LLM Capabilities for Backward Reasoning in Math Word Problems