Austria

Many challenging reasoning tasks require not just rapid, intuitive responses, but a more deliberate, multi-step approach. Recent progress in large language models (LLMs) highlights an important shift from the “System 1” way of quick reactions to the “System 2” style of reflection-and-correction problem solving. However, current benchmarks heavily rely on the final-answer accuracy, leaving much of a model’s intermediate reasoning steps unexamined. This fails to assess the model’s ability to reflect and rectify mistakes within the reasoning process. To bridge this gap, we introduce FINEREASON, a logic-puzzle benchmark for systematic evaluation of LLMs’ reasoning capabilities. Each puzzle can be decomposed into atomic steps, making it ideal for rigorous validation of intermediate correctness. Building on this, we introduce two tasks: state checking and state transition, for a comprehensive evaluation of how models assess the current situation and plan the next move. To support broader research, we also provide a puzzle training set aimed at enhancing general reasoning. We show that models trained on our state checking and transition data demonstrate gains in mathematical reasoning by up to 5.1%.

ACL 2025

FineReason: Evaluating and Improving LLMs&#39; Deliberate Reasoning through Reflective Puzzle Solving

system 2 reasoning

puzzle solving

llm reasoning

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

FineReason: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving

technical paper

### 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)

With the rapid advancement of Large Vision-Language Models (VLMs), concerns about their ‌potential misuse and abuse have grown rapidly. Prior research has exposed VLMs' vulnerability to jailbreak attacks, where carefully crafted inputs can lead the model to produce content that violates ethical and legal standards. However, current jailbreak methods often fail against cutting-edge models such as GPT-4o. We attribute this to the over-exposure of harmful content and the absence of stealthy malicious guidance. 
In this work, we introduce a novel jailbreak framework: Multi-Modal Linkage (MML) Attack. Drawing inspiration from cryptography, MML employs an encryption-decryption process across text and image modalities to mitigate the over-exposure of malicious information. To covertly align the model’s output with harmful objectives, MML leverages a technique we term evil alignment, framing the attack within the narrative context of a video game development scenario. 
Extensive experiments validate the effectiveness of MML. Specifically, MML jailbreaks GPT-4o with attack success rates of 99.40\% on SafeBench, 98.81\% on MM-SafeBench, and 99.07\% on HADES-Dataset. Our code is available at https://github.com/wangyu-ovo/MML.

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Federated fine-tuning for Large Language Models (LLMs) has recently gained attention due to the heavy communication overhead of transmitting large model updates. Low Rank Adaptation (LoRA) has been proposed as a solution, yet its application in federated learning is complicated by discordance in aggregation. Existing methods addressing this discordance often suffer from performance degradation at low ranks in heterogeneous data settings. In response, we introduce LoRA-A^2
(Low Rank Adaptation with Alternating freeze and Adaptive rank selection), which demonstrates robustness in challenging settings with low ranks and high data heterogeneity. Our experimental findings reveal that LoRA-A^2
maintains performance even under extreme heterogeneity and low rank conditions, achieving up to a 99.8% reduction in uploaded parameters compared to full fine-tuning without compromising performance. This adaptive mechanism boosts robustness and communication efficiency in federated fine-tuning, enabling the practical deployment of LLMs in resource-constrained environments.

Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients

Large Language Models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities from few-shot demonstration exemplars. Recent learning-based demonstration selection methods have proven beneficial to ICL by choosing more useful exemplars. While these methods generally assume they learn better similarity measurements between exemplars and test cases from the proxy task, what kinds of similarities are captured by them and are vital to performing ICL still need to be explored. To dive into this question, we analyze the working mechanism of learning-based demonstration selection methods and empirically identify two essential factors of their similarity measurements: 1) Integrating task-agnostic similarities of different levels between the input of exemplars and test cases; 2) Incorporating task-specific similarity between the output of exemplars and test cases. We validate these two findings through extensive quantitative analysis across ten datasets and various LLMs. Based on these insights, we introduce two simplified exemplar selection methods, MLSM and TTF, catering to task-agnostic and task-specific demands to eliminate costly data collection. The effectiveness of both methods evince our findings again and pave the way for future studies.

Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning

Metaphors are a crucial way for humans to express complex or subtle ideas by comparing one concept to another, often from a different domain. However, many large language models (LLMs) struggle to interpret and apply metaphors in multi-agent language games, hindering their ability to engage in covert communication and semantic evasion, which are crucial for strategic communication. To address this challenge, we introduce CoMet, a framework that enables LLM-based agents to engage in metaphor processing. CoMet combines a hypothesis-based metaphor reasoner with a metaphor generator that improves through self-reflection and knowledge integration. This enhances the agents' ability to interpret and apply metaphors, improving the strategic and nuanced quality of their interactions. We evaluate CoMet on two multi-agent language games—Undercover and Adversarial Taboo—which emphasize "covert communication'' and "semantic evasion''. Experimental results demonstrate that CoMet significantly enhances the agents' ability to communicate strategically using metaphors.

CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games

Opinion survey research is a crucial method used by social scientists for understanding societal beliefs and behaviors. Traditional methodologies often entail high costs and limited scalability, while current automated methods such as opinion synthesis exhibit severe biases and lack traceability. In this paper, we introduce SurveyPilot, a novel finite‐state orchestrated agentic framework that automates the collection and analysis of human opinions from social media platforms. SurveyPilot addresses the limitations of pioneering approaches by (i) providing transparency and traceability in each state of opinion collection and (ii) incorporating several techniques for mitigating biases, notably with a novel genetic algorithm for improving result diversity. Our extensive experiments reveal that SurveyPilot achieves a close alignment with authentic survey results across multiple domains, observing average relative improvements of 68,98% and 51,37% when comparing to opinion synthesis and agent-based approaches. Implementation of SurveyPilot is available on https://github.com/thanhpv2102/SurveyPilot.

SurveyPilot: an Agentic Framework for Automated Human Opinion Collection from Social Media

Expressive zero-shot voice conversion (VC) is a critical and challenging task that aims to transform the source timbre into an arbitrary unseen speaker while preserving the original content and expressive qualities. Despite recent progress in zero-shot VC, there remains considerable potential for improvements in speaker similarity and speech naturalness. Moreover, existing zero-shot VC systems struggle to fully reproduce paralinguistic information in highly expressive speech, such as breathing, crying, and emotional nuances, limiting their practical applicability. To address these issues, we propose Takin-VC, a novel expressive zero-shot VC framework via adaptive hybrid content encoding and memory-augmented context-aware timbre modeling. Specifically, we introduce an innovative hybrid content encoder that incorporates an adaptive fusion module, capable of effectively integrating quantized features of the pre-trained WavLM and HybridFormer in an implicit manner, so as to extract precise linguistic features while enriching paralinguistic elements. For timbre modeling, we propose advanced memory-augmented and context-aware modules to generate high-quality target timbre features and fused representations that seamlessly align source content with target timbre. To enhance real-time performance, we advocate a conditional flow matching model to reconstruct the Mel-spectrogram of the source speech. Experimental results show that our Takin-VC consistently surpasses state-of-the-art VC systems, achieving notable improvements in terms of speech naturalness, speech expressiveness, and speaker similarity, while offering enhanced inference speed.

Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling

Argumentation scheme mining is the task of automatically identifying reasoning mechanisms behind argument inferences. These mechanisms provide insights into underlying argument structures and guide the assessment of natural language arguments. Research on argumentation scheme mining, however, has always been limited by the scarcity of large enough publicly available corpora containing scheme annotations. In this paper, we present the first state-of-the-art results for mining argumentation schemes in natural language dialogue. For this purpose, we create QT-Schemes, a new corpus of 441 arguments annotated with 24 argumentation schemes. Using this corpus, we leverage the capabilities of LLMs and Transformer-based models, pre-training them on a large corpus containing textbook-like argumentation schemes and validating their applicability in real-world scenarios.

Mining Complex Patterns of Argumentative Reasoning in Natural Language Dialogue

Massive high-quality data, both pre-training raw texts and post-training annotations, have been carefully prepared to incubate advanced large language models (LLMs). In contrast, for information extraction (IE), pre-training data, such as BIO-tagged sequences, are hard to scale up. We show that IE models can act as free riders on LLM resources by reframing next-token \emph{prediction} into \emph{extraction} for tokens already present in the context. Specifically, our proposed next tokens extraction (NTE) paradigm learns a versatile IE model, \emph{Cuckoo}, with 102.6M extractive data converted from LLM's pre-training and post-training data. Under the few-shot setting, Cuckoo adapts effectively to traditional and complex instruction-following IE with better performance than existing pre-trained IE models. As a free rider, Cuckoo can naturally evolve with the ongoing advancements in LLM data preparation, benefiting from improvements in LLM training pipelines without additional manual effort.

Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM’s Nest

Syntactic language models (SLMs) enhance Transformers by incorporating syntactic biases through the modeling of linearized syntactic parse trees alongside surface sentences. This paper focuses on compositional SLMs that are based on constituency parse trees and contain explicit bottom-up composition of constituent representations. We identify key aspects of design choices in existing compositional SLMs and propose a unified framework encompassing both existing models and novel variants. We conduct a comprehensive empirical evaluation of all the variants in our framework across language modeling, syntactic generalization, summarization, and inference efficiency. Based on the experimental results, we make multiple recommendations on the design of compositional SLMs. Our code is released at https://github.com/zhaoyd1/compositional_SLMs.

A Systematic Study of Compositional Syntactic Transformer Language Models

Current Large Language Models (LLMs) are predominantly designed with English as the primary language, and even the few that are multilingual tend to exhibit strong English-centric biases. Much like speakers who might produce awkward expressions when learning a second language, LLMs often generate unnatural outputs in non-English languages, reflecting English-centric patterns in both vocabulary and grammar. Despite the importance of this issue, the naturalness of multilingual LLM outputs has received limited attention. In this paper, we address this gap by introducing novel automatic corpus-level metrics to assess the lexical and syntactic naturalness of LLM outputs in a multilingual context. Using our new metrics, we evaluate state-of-the-art LLMs on a curated benchmark in French and Chinese, revealing a tendency towards English-influenced patterns. To mitigate this issue, we also propose a simple and effective alignment method to improve the naturalness of an LLM in a target language and domain, achieving consistent improvements in naturalness without compromising the performance on general-purpose benchmarks. Our work highlights the importance of developing multilingual metrics, resources and methods for the new wave of multilingual LLMs.

Downloads

Next from ACL 2025

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Similar lecture

Puzzle Solving using Reasoning of Large Language Models: A Survey