Papers with LRM
The Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI (2026.eacl-short)
Copied to clipboard
| Challenge: | Large Reasoning Models (LRMs) are highly effective on mathematical, scientific, and other question-answering tasks. |
| Approach: | They compare an LRM's reasoning in English to that of a multilingual question . they find that English reasoning traces exhibit a substantially higher presence of cognitive behaviors . |
| Outcome: | The LRMs generate reasoning sequences in English, but the language of the question is not. |
One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL (2025.acl-industry)
Copied to clipboard
Hyungjoo Chae, Dongjin Kang, Jihyuk Kim, Beong-woo Kwak, Sunghyun Park, Haeju Park, Jinyoung Yeo, Moontae Lee, Kyungjae Lee
| Challenge: | Existing large reasoning models are limited by their closed nature and high API costs and safety issues. |
| Approach: | They propose to build a long CoT dataset with existing short CoT LLMs that are not trained for inference-time scaling. |
| Outcome: | The proposed model achieves quality comparable to—or slightly below—R1 and is able to think longer and provide control over the thought budget to better manage the overthinking problem. |
Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication (2026.acl-industry)
Copied to clipboard
| Challenge: | Legal texts contain computational legal clauses that exceed the semantic complexity of the realworld activities they govern. |
| Approach: | They propose a neuro-symbolic approach to legal adjudication using an LLM . they use a typed graph intermediate representation to translate a legal text into a deterministic contract language . |
| Outcome: | The proposed system reduces compute costs by over 90% in high-volume workflows while satisfying auditability requirements. |
Think Outside the Policy: In-Context Steered Policy Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods exhibit limited exploration due to reliance on on-policy rollouts which are limited to the current policy’s distribution, resulting in narrow trajectory diversity. |
| Approach: | They propose a framework that leverages the in-context learning capability of Large Reasoning Models to provide expert guidance using existing datasets. |
| Outcome: | The proposed framework improves RLVR performance and training stability on mathematical reasoning benchmarks. |
CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to unlearning large reasoning models do not remove unwanted knowledge from CoT traces or interfere with the reasoning process. |
| Approach: | They propose a framework that targets the CoT reasoning in Large Reasoning Models by generating a valid counterfactual reasoning trace for preference tuning. |
| Outcome: | Experiments on large LRMs show that CiPO completely removes knowledge from the intermediate CoT steps and the final answer while preserving the reasoning abilities of LRM. |
Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills (2025.emnlp-main)
Copied to clipboard
Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
| Challenge: | Existing methods for LRM unlearning overlook critical information leakage in reasoning traces, even when final answers are successfully removed. |
| Approach: | They propose a method that suppresses reasoning traces while preserving the model's general reasoning ability. |
| Outcome: | The proposed method significantly reduces reasoning trace leakage and achieves strong performance across reasoning and safety benchmarks, including WMDP, StrongReject, JBB-Behaviors and WildJailbreak. |
Enhancing Lexical Relation Mining with Structured Sememe Knowledge (2026.acl-long)
Copied to clipboard
| Challenge: | Existing top-performing methods for Lexical Relation Mining rely on pre-trained language models yet fail to distinguish nuanced lexical relations. |
| Approach: | They propose a framework to leverage structured sememe knowledge to enhance LRC and LE. |
| Outcome: | The proposed method outperforms existing methods on benchmarks and outperformed the LLMs. |
ThinkSwitcher: When to Think Hard, When to Think Fast (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large reasoning models excel at solving complex tasks by leveraging long chain-of-thought (CoT) reasoning. |
| Approach: | They propose a framework that enables a single LRM to dynamically switch between short and long CoT modes based on task complexity. |
| Outcome: | The proposed framework reduces computational cost by 20-30% while maintaining high accuracy on complex tasks. |
TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Reasoning Models suffer from high inference latency due to autoregressive reasoning . SpecReason adopts a polling-based design that repeatedly invokes the LRM for verification at every step . |
| Approach: | They propose a trigger-based collaborative reasoning framework that delegates most reasoning to the SRM and activates LRM intervention only when necessary. |
| Outcome: | The proposed framework reduces latency and API cost by 73.3% under edge–cloud conditions. |
Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation (2026.findings-acl)
Copied to clipboard
Wei-Rui Chen, Vignesh Kothapalli, Ata Fatahibaarzi, Hejian Sang, Shao Tang, Qingquan Song, Zhipeng Wang, Muhammad Abdul-Mageed
| Challenge: | a large reasoning model (LRM) training on large amounts of reasoning data is computationally expensive. |
| Approach: | They propose a method to quantify computation-quality tradeoffs as a function of sequence length. |
| Outcome: | The proposed method reduces training time, memory and FLOPs by 50% on long training sequences while retaining the full-sequence performance. |
Understanding LLM Reasoning for Abstractive Summarization (2026.findings-acl)
Copied to clipboard
| Challenge: | Explicit reasoning strategies improve reference-based quality, but weaken factual grounding, whereas implicit reasoning in LRMs shows the opposite tendency. |
| Approach: | They adapt general reasoning strategies to the summarization setting and conduct a large-scale comparative study of 8 reasoning strategies and 3 Large Reasoning Models (LRMs) they find a trade-off between summary quality and factual faithfulness. |
| Outcome: | The proposed reasoning strategies and 3 Large Reasoning Models (LRMs) are compared with 8 reasoning strategies across 8 datasets. |
Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theory (2025.emnlp-main)
Copied to clipboard
Ming Li, Nan Zhang, Chenrui Fan, Hong Jiao, Yanbin Fu, Sydney Peters, Qingshu Xu, Robert Lissitz, Tianyi Zhou
| Challenge: | Large Reasoning Models (LRMs) generate extensive chain-of-thought reasoning, but we lack a principled framework for understanding how these thoughts are structured. |
| Approach: | They propose a method to analyze the reasoning traces of Large Reasoning Models using Schoenfeld’s Episode Theory. |
| Outcome: | The proposed framework provides a theoretically grounded methodology for interpreting LRM cognition and enables future work on more controllable and transparent reasoning systems. |
Red Teaming Large Reasoning Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, but they introduce safety and reliability risks, such as CoT-hijacking and prompt-induced inefficiencies. |
| Approach: | They propose a unified benchmark to assess the trustworthiness of Large Reasoning Models. |
| Outcome: | The proposed benchmark evaluates truthfulness, safety and efficiency on 26 models. |
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities (2025.findings-acl)
Copied to clipboard
Fengqing Jiang, Zhangchen Xu, Yuetai Li, Luyao Niu, Zhen Xiang, Bo Li, Bill Yuchen Lin, Radha Poovendran
| Challenge: | Emerging large reasoning models (LRMs) leverage long chain-of-thought (CoT) reasoning to enhance their reasoning capabilities. |
| Approach: | They conduct a systematic study of LRM safety using human annotations to assess their safety. |
| Outcome: | The proposed safety measures are compared to state-of-the-art models on strong and wildjailbreak datasets. |
MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MEXA is a training-free framework that performs modality- and task-aware aggregation of multiple expert models to enable effective multimodal reasoning across diverse domains. |
| Approach: | MEXA is a training-free framework that performs modality- and task-aware aggregation of multiple expert models. |
| Outcome: | MEXA performs modality- and task-aware aggregation of multiple expert models . it generates interpretable textual reasoning outputs and reasons over them using a Large Reasoning Model (LRM) MEX A consistently delivers performance improvements over strong multimodal benchmarks . |
ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments (2026.acl-long)
Copied to clipboard
| Challenge: | Existing defenses for Large Reasoning Models (LRMs) depend on costly fine-tuning and additional expert knowledge, which limits their scalability. |
| Approach: | They propose an inference-time safeguard for Large Reasoning Models that injects safety aha moments into the reasoning process to guide the model towards harmless yet helpful reasoning. |
| Outcome: | The proposed safeguard outperforms nine existing safeguards while avoiding common exaggerated safety issues. |
Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Reasoning Models (LRMs) are often bottlenecked by the high cost of output tokens. |
| Approach: | They propose a lightweight, turnkey component for Large Reasoning Models that is minimally invasive to its reasoning trajectory. |
| Outcome: | The proposed component is lightweight and low overhead, and lacks semantic value. |
AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large reasoning models (LRMs) generate coherent reasoning paths before conclusions, but they introduce new vulnerabilities. |
| Approach: | They propose a framework that leverages a weaker but less-aligned model to simulate execution reasoning for initial hijacking attempts and iteratively refines attacks by exploiting reasoning patterns leaked through the target LRM’s refusals. |
| Outcome: | The proposed framework achieves 100% success rate within one or few turns, neutralizing reasoning-based defenses even when evaluated by robustly aligned external models. |