CLARO: Controlled Attribute-Driven Reasoning Optimization for Efficient Chain-of-Thought (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent approaches guide reasoning length through token penalties or truncation, risking the omission of necessary steps. |
| Approach: | They propose a framework to internalize conciseness and attribute-driven reasoning optimization . they propose guiding models to embed high-quality structural attributes within a token budget . |
| Outcome: | The proposed method outperforms state-of-the-art models across benchmarks yielding accuracy gains of up to 63.6%. |
Similar Papers
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. |
Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing frameworks for guiding a language model in reasoning tasks are limited by their tendency to generate low-quality rationales that are repetitive and vacuous. |
| Approach: | They propose a framework that leverages a lightweight language model for guiding a black-box large LM in reasoning tasks. |
| Outcome: | The proposed framework outperforms baselines in answer prediction accuracy. |
VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision (2026.acl-long)
Copied to clipboard
| Challenge: | Empirical evaluations demonstrate that VCORE achieves the strongest overall average performance, with especially clear gains on lower-capacity models. |
| Approach: | They propose a framework that reformulates supervision as a constrained optimization problem. |
| Outcome: | Empirical evaluations show that VCORE achieves the strongest overall average performance, with especially clear gains on lower-capacity models. |
DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) often prioritize reasoning over adherence to detailed instructions due to high computational costs and limited parameter access. |
| Approach: | They propose a lightweight framework that guides small language models to refine LLMs’ outputs through chain-of-thought correction. |
| Outcome: | The proposed framework improves the average format accuracy and content correctness of LLM outputs by 35.4% and 29.4%, respectively, achieving state-of-the-art (SOTA) performance over other competitive baselines. |
Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) often produce unnecessarily long explanations that reduce efficiency. |
| Approach: | They propose a length-aware reward that selectively penalizes insignificance tokens . they also propose 'dynamic length control' that encourages more detailed reasoning . |
| Outcome: | The proposed method reduces response length while maintaining correctness, the authors show . it selectively penalizes insignificance tokens while maintaining accuracy . |
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning for LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to reinforcement learning with verifiable reward (RLVR) are limited by difficulty or lack of exploration. |
| Approach: | They propose a self-evolving curriculum learning framework based on chain-of-thought reasoning optimization that constrains exploration space by self-generating and verifying CoT trajectories. |
| Outcome: | The proposed framework enables LLMs to solve previously unsolved problems without external supervision and is compatible with various RL fine-tuning methods. |
Think Better, Not Longer: Token-Level Marginal Utility for Efficient Reasoning in Large Reasoning Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large reasoning models (LRMs) generate explicit Chain-of-Thought rationales, but often suffer from "overthinking". |
| Approach: | They propose a unified training framework to synthesize concise reasoning chains by identifying tokens that reduce the model’s likelihood of the correct answer. |
| Outcome: | Experiments on deepSeek-R1-Distill-Qwen backbones show that MUTO yields better efficiency-accuracy Pareto frontier. |
Think Faster Than Words: Efficient LLM Chain-of-Thought Reasoning via Dynamic Shortcut Decoding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods that prune or employ early stopping to reduce latency often compromise reasoning reliability. |
| Approach: | They propose a shortcut decoding framework that integrates probes over internal hidden states with step-level entropy to detect convergence of reasoning during generation and adaptively selects between a fast-exit path and a stability-verified path to remove redundant steps while preserving answer correctness. |
| Outcome: | The proposed framework reduces token usage by approximately 35% and maintains accuracy comparable to full CoT decoding. |
Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning (2024.acl-long)
Copied to clipboard
| Challenge: | Recent studies focus on enhancing large-scale language models' reasoning abilities, but the research question of how to GSM8K Performance vs. computational cost remains. |
| Approach: | They propose to train small-scale language models with their own outputs to avoid relying on large models' outputs. |
| Outcome: | The proposed approach outperforms baseline models with comparable sizes while minimizing the required compute. |
Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Chain-of-thought (CoT) prompting is a technique to enhance the reasoning abilities of Large language models (LLMs) however, the reasoning chains of demonstrations are observed to be prone to errors, which can lead to incorrect reasoning during inference. |
| Approach: | They propose an iterative bootstrapping technique to enhance the reasoning abilities of Large language models (LLMs) by generating a series of reasoning steps to obtain the answer, and using the reasoning chains as exemplars to demonstrate the task. |
| Outcome: | The proposed method improves the performance of Large language models (LLMs) on three reasoning tasks on ten datasets. |