Papers with reasoning capabilities of
LogiTorch: A PyTorch-based library for logical reasoning on natural language (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Logical reasoning on natural language is one of the most challenging tasks for deep learning models. |
| Approach: | They propose a library that includes logical reasoning benchmarks and models . they use a dataset to run the library or fine tune the models with different hyperparameters . |
| Outcome: | This library includes logical reasoning benchmarks, models, utility functions and co-reference resolution. |
Improving LLM Reasoning through Interpretable Role-Playing Steering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for role-playing rely on prompt engineering, which lacks stability and interpretability. |
| Approach: | They propose a framework that extracts latent representations from role-play prompts and constructs a steering vector that can be injected into the model's residual stream with controllable intensity. |
| Outcome: | The proposed framework extracts latent representations from role-play prompts, selects the most relevant features based on activation patterns, and constructs a steering vector that can be injected into the model’s residual stream with controllable intensity. |
The Hallucination Tax of Reinforcement Finetuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Reinforcement finetuning (RFT) has become a standard approach for enhancing the reasoning capabilities of large language models (LLMs). |
| Approach: | They propose to incorporate 10% SUM into RFT to restore appropriate refusal behavior with minimal accuracy trade-offs on solvable tasks. |
| Outcome: | The proposed approach reduces model refusal rates by more than 80%, which significantly increases model’s tendency to hallucinate. |
TokenSkip: Controllable Chain-of-Thought Compression in LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Chain-of-Thought (CoT) has been proven effective in enhancing the reasoning capabilities of large language models (LLMs). |
| Approach: | They propose a chain-of-thought (CoT) prompting approach that enables LLMs to selectively skip less important tokens, allowing for controllable CoT compression. |
| Outcome: | Experiments show that TokenSkip reduces CoT token usage while preserving strong reasoning performance. |
Progressive Multimodal Reasoning via Active Retrieval (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to improve multimodal large language models' reasoning performance are limited. |
| Approach: | They propose a framework to progressively improve multimodal reasoning capabilities . they propose active retrieval and Monte Carlo tree search to improve MLLMs' reasoning . |
| Outcome: | The proposed framework improves multimodal reasoning capabilities in multimodal large language models. |
Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on neurons focus on emotion and rhetoric, neglecting their intrinsic connections. |
| Approach: | They propose a framework for fine-grained steering of emotion and rhetoric in large language models . they propose 'neuro-based' masking method that integrates multi-dimensional screening . |
| Outcome: | The proposed method achieves directed induction of non-target sentences and enhancement of emotion tasks via rhetoric neurons. |
Unveiling Confirmation Bias in Chain-of-Thought Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Chain-of-thought (CoT) prompting has been widely adopted to enhance the reasoning capabilities of large language models (LLMs). |
| Approach: | They propose to examine how internal beliefs affect reasoning generation and reasoning-guided answer prediction in CoT by decomposing CoT into a two-stage process. |
| Outcome: | The proposed model beliefs affect reasoning generation and reasoning-guided answer prediction in CoT, and the results provide strong evidence of confirmation bias in LLMs. |
ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing CoT synthesis approaches focus on simpler reasoning tasks and result in inconsistent CoT prompts. |
| Approach: | They propose a framework for automatic generation of superior CoT prompts based on three major evolution strategies . they propose 'step-level debating' method where multiple debaters discuss each reasoning step to arrive at the correct answer. |
| Outcome: | The proposed framework can generate superior CoT prompts from a CoT dataset. |
ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLM (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing verification methods rely on unstructured text corpora to break down claims . despite strong reasoning abilities, modern LLMs struggle with modular pipelines . |
| Approach: | They propose a framework that integrates knowledge graphs with LLM reasoning . they propose KGs provide structured, semantically rich representations . |
| Outcome: | The proposed framework outperforms baselines on the FactKG dataset by 9%-12% accuracy points across multiple categories. |
HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent benchmarks have attempted to identify and explain hate speech but lack the reasoning to supervise detection models. |
| Approach: | They propose a framework that uses large language models to fill in the gaps in hate speech explanations by using existing annotations. |
| Outcome: | The proposed framework outperforms baselines on SBIC and Implicit Hate using model-generated data and improves generalization to unseen datasets. |
DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Chain-of-Thought prompting has improved the reasoning capabilities of Large Language Models (LLMs) but it is ineffective or detrimental to the performance on reasoning tasks in Smaller Language Model (SLMs) with less than 10 billion parameters. |
| Approach: | They propose a Dialogue-guided Chain-of-Thought method to improve the reasoning capabilities of Large Language Models (LLMs) by generating intermediate reasoning steps in a dialogue format to guide the model to the final answer. |
| Outcome: | The proposed method can achieve significant performance gains over state-of-the-art competitors on four arithmetic reasoning datasets. |
Enhancing Large Language Models through Transforming Reasoning Problems into Classification Tasks (2024.lrec-main)
Copied to clipboard
Tarun Raheja, Raunak Sinha, Advit Deepak, Will Healy, Jayanth Srinivasa, Myungjin Lee, Ramana Kompella
| Challenge: | Existing approaches to improve LLMs' reasoning capabilities for constraint satisfaction problems (CSPs) are needed to solve complex tasks. |
| Approach: | They propose a method that leverages the LLM's ability to decide when to call a function from a set of logical-linguistic primitives, each of which can interact with a local “scratchpad” memory and logical inference engine. |
| Outcome: | The proposed method improves the reasoning capabilities of large language models for constraint satisfaction problems by 40% over baselines. |
Socratic Style Chain-of-Thoughts Help LLMs to be a Better Reasoner (2025.findings-acl)
Copied to clipboard
| Challenge: | Synthetic data generation is a promising approach to enhance reasoning capabilities of large language models. |
| Approach: | They propose a multi-agent debate framework based on the Socratic questioning strategy . they use socratic questions to deepen the thinking process and broaden it to motivate self-reflection . |
| Outcome: | The proposed framework outperforms existing methods on math and code generation tasks while maintaining affordable costs. |
How Ambiguous Are the Rationales for Natural Language Reasoning? A Simple Approach to Handling Rationale Uncertainty (2025.coling-main)
Copied to clipboard
| Challenge: | Language models have made significant progress on complex reasoning tasks, but it is impossible to obtain perfect rationales from models or even from humans. |
| Approach: | They propose a way to guide models to choose between two different reasoning paths depending on the ambiguity of rationales. |
| Outcome: | The proposed approach leads to robust performance in adversarial scenarios where rationale quality is inconsistent. |
FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging (2025.acl-long)
Copied to clipboard
Zichen Tang, Haihong E, Ziyan Ma, Haoyang He, Jiacheng Liu, Zhongjun Yang, Zihua Rong, Rongjin Li, Kun Ji, Qing Huang, Xinyang Hu, Yang Liu, Qianhe Zheng
| Challenge: | Compared to existing benchmarks, FinanceReasoning provides three key advancements: (1) credibility; (2) comprehensiveness; (3) numerical precision; (4) complexity; (5) complexity; and (6) complexity. |
| Approach: | They propose a benchmark to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems. |
| Outcome: | The proposed benchmark exceeds existing benchmarks in 67.8% of financial concepts and formulas and is credible, comprehensive, and challenging. |
ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multi-agent systems (MAS) are limited by poor flexibility and scalability, with underdeveloped optimization strategies. |
| Approach: | They propose a task graph generation and a reward-driven two-stage agent selection process to integrate multi-agent systems to improve their reasoning capabilities. |
| Outcome: | The proposed model outperforms existing methods on Math-MAS and SciBench-MAS SciBech, while other methods completely fail. |
Large Language Models Are Reasoning Teachers (2023.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that chain-of-thought (CoT) prompting can elicit language models to solve complex reasoning tasks step-by-step. |
| Approach: | They propose a method that uses large model samples as reasoning teachers to fine-tune smaller models. |
| Outcome: | The proposed method outperforms prompt-based methods and the teacher model in many tasks and extends it by leveraging the teacher's ability to generate multiple rationales for each original sample. |
Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions (2025.acl-long)
Copied to clipboard
| Challenge: | Recent work suggests using logical formalisms coupled with external symbolic solvers to solve complex tasks. |
| Approach: | They propose a framework to disentangle content from logical reasoning without a complete formalisation. |
| Outcome: | The proposed methods improve CoT-based methods by up to 8% accuracy on challenging adversarial variations on both natural language and symbolic reasoning tasks. |
Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs). |
| Approach: | They propose a model-free method that refines credit assignment by leveraging the model's internal uncertainty signals. |
| Outcome: | Extensive experiments on five mathematical reasoning benchmarks show that the proposed method outperforms strong RLVR baselines on multiple model scales, including 1.5B and 7B. |
A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)
Copied to clipboard
Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo
| Challenge: | Existing research on reinforcement learning for LLMs under data scarcity has not been unified. |
| Approach: | They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric. |
| Outcome: | The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area. |
AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) has emerged as an effective approach for enhancing the reasoning capabilities of large language models. |
| Approach: | They propose an algorithm that optimizes cross-entropy loss using advantages enhanced through a margin-based estimation scheme. |
| Outcome: | Experimental results show that AAPO improves group relative advantage estimation compared to other methods. |
FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for multimodal large language models lack data contamination and complex queries . financial cross-modal multi-hop reasoning is difficult to evaluate and requires precise cross-module reasoning . |
| Approach: | They propose a benchmark to analyze the reasoning capabilities of multimodal large language models. |
| Outcome: | The proposed model is categorized into three difficulty levels—easy, medium, and hard—for step-by-step evaluation. |
MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning (2026.findings-acl)
Copied to clipboard
Xukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Bohan Zeng, Jinbo Hu, Hao Liang, Junbo Niu, Xuchen Li, Ruitao Wu, Ruichuan An, Yang Shi, Liu Liu, Qiang Liu, Zhouchen Lin, Xu-Yao Zhang, Wentao Zhang, Bin Dong
| Challenge: | Existing benchmarks designed to evaluate the reasoning capabilities of large models are limited in scope and lack flexibility to adapt difficulty according to evolving reasoning capacities of models. |
| Approach: | They propose a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. |
| Outcome: | The proposed benchmark incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. |
Revisiting Entropy in Reinforcement Learning for Large Reasoning Models (2026.findings-acl)
Copied to clipboard
Renren Jin, Pengzhi Gao, Yuqi Ren, Zhuowen Han, Tongxuan Zhang, Wuwei Huang, Wei Liu, Jian Luan, Deyi Xiong
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has emerged as a paradigm for enhancing the reasoning capabilities of large language models. |
| Approach: | They propose a positive-advantage reweighting approach that regulates model entropy by adjusting the loss weights assigned to tokens with positive advantages during RLVR training. |
| Outcome: | The proposed approach regulates model entropy by adjusting loss weights assigned to tokens with positive advantages during RLVR training while maintaining competitive performance. |
Reasoning-Guided Exploration for Online DPO (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work has aimed to enhance reasoning capabilities of language models, but these methods are limited to domains with objectively verifiable answers. |
| Approach: | They propose a self-play framework to improve reasoning on general-domain data. |
| Outcome: | Experiments show that the proposed framework improves reasoning performance on general-domain data while maintaining competitive performance on verifiable academic benchmarks. |
DARL: Encouraging Diverse Answers for General Reasoning without Verifiers (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent efforts such as RLPR have extended RLVR to general domains, enabling training on broader datasets and achieving improvements over RL PR. |
| Approach: | They propose a framework that encourages the generation of diverse answers within a controlled deviation range from the reference while preserving alignment with it. |
| Outcome: | Extensive experiments on 13 benchmarks show that DARL surpasses RLPR in both reasoning accuracy and output diversity. |
Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model (2025.acl-long)
Copied to clipboard
| Challenge: | Existing Chain-of-Thought (CoT) methods struggle with consistency and verification in complex reasoning tasks. |
| Approach: | They propose a framework that integrates structured knowledge representation with learned planning. |
| Outcome: | The proposed framework outperforms existing Chain-of-Thought (CoT) methods on math reasoning, logical reasoning, and coding tasks. |
SCALER: Synthetic Scalable Adaptive Learning Environment for Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) is a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. |
| Approach: | They propose a framework that sustains effective learning signals through adaptive environment design that transforms real-world programming problems into verifiable reasoning environments with controllable difficulty and unbounded instance generation. |
| Outcome: | The proposed framework outperforms baselines across diverse reasoning benchmarks and exhibits more stable, long-horizon training dynamics. |
Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains (2026.acl-long)
Copied to clipboard
Zhonghang Yuan, Zhefan Wang, Fang Hu, Zihong Chen, Jinzhe Li, Gang Li, Jie Ying, Huanjun Kong, Songyang Zhang, Nanqing Dong
| Challenge: | Recent large language models (LLMs) have demonstrated remarkable progress in reasoning, but their applications on knowledge-intensive domains have not been explored due to the scarcity of high-quality verifiable data. |
| Approach: | They propose a framework that extends reinforcement learning with verifiable rewards (RLVR) to knowledge-intensive domains through automated verififiability data synthesis while enabling verification of the LLM's reasoning process. |
| Outcome: | Extensive experiments show that the proposed framework enhances the reasoning of large language models in knowledge-intensive domains without significantly compromising the model’s general capabilities. |
Data Efficient RLVR via Off-Policy Influence Guidance (2026.acl-long)
Copied to clipboard
Erle Zhu, Dazhi Jiang, Yuan Wang, Xujun Li, Jiale Cheng, Yuxian Gu, Yilin Niu, Aohan Zeng, Jie Tang, Minlie Huang, Hongning Wang
| Challenge: | Existing data selection methods for RLVR are heuristic-based, lacking theoretical guarantees and generalizability. |
| Approach: | They propose an off-policy influence estimation method that approximates data influence using offline trajectories. |
| Outcome: | The proposed method reduces the computational cost of policy rollouts and improves storage and computation efficiency. |