To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples (2026.acl-long)
Copied to clipboard
| Challenge: | Chain-of-thought (CoT) prompting and in-context learning (ICL) have unlocked significant reasoning capabilities in large language models (LLMs). |
| Approach: | They propose a meta-training technique to learn reasoning tasks in-context using CoT examples. |
| Outcome: | The proposed methods improve performance on novel reasoning tasks even when there are no CoT examples available in-context. |
Similar Papers
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters (2023.acl-long)
Copied to clipboard
| Challenge: | Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs). |
| Approach: | They propose to use Chain-of-Thought (CoT) prompting to encourage the LLM to generate intermediate rationales for solving a problem by providing a series of reasoning steps in the demonstrations. |
| Outcome: | The proposed model can generate coherent lines of reasoning even with invalid demonstrations while still generating coherent lines during inference. |
CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations (2025.acl-long)
Copied to clipboard
| Challenge: | In-context learning and CoT are still poorly understood, but the precise mechanisms and architectural factors driving ICL and Co T are still unclear. |
| Approach: | They propose a framework and methodology to generate synthetic tokenized datasets and study chain-of-thought (CoT) in-context learning in language models. |
| Outcome: | The proposed framework and methodology allows fine grained control over the complexity of in-context examples by decoupling causal structure from underlying token processing functions. |
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens (2026.findings-acl)
Copied to clipboard
Chengshuai Zhao, Zhen Tan, Pingchuan Ma, Dawei Li, Bohan Jiang, Yancheng Wang, Yingzhen Yang, Huan Liu
| Challenge: | Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning from large language models (LLMs). |
| Approach: | They propose a data distribution lens to understand when and why CoT reasoning fails . they propose 'data-based' training that trains LLMs from scratch . |
| Outcome: | The proposed model enables models to generate reasoning trajectories that approximate those observed during training. |
CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Long chain-of-thought (CoT) prompting often slows or even degrades performance on fast, intuitive "System-1" tasks. |
| Approach: | They introduce a method that deliberately restricts reasoning to a small, fixed set of connector phrases, steering the model toward concise and well-structured explanations. |
| Outcome: | The method achieves 85% on GSM8K and 40% on GPQA while also surpassing the baseline by over 20%. |
AS-ES Learning: Towards efficient CoT learning in small models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to induce Chain-of-Thought (CoT) in LLMs are limited and do not consider the importance of efficiently utilizing existing CoT data. |
| Approach: | They propose a new training paradigm which exploits the inherent information in CoT for iterative generation. |
| Outcome: | The proposed training paradigm surpasses direct seq2seq training on CoT-extensive tasks without data augmentation or altering the model itself. |
Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods train small language models to learn long rationales in one iteration. |
| Approach: | They propose a method that uses a heuristic search to divide rationale into internal chunks . they propose CWT, which uses CWt to focus SLM on learning from only one chunk per iteration. |
| Outcome: | The proposed method can guide a large language model (LLM) in reasoning tasks. |
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression (2026.acl-long)
Copied to clipboard
Chengzhengxu Li, Xiaoming Liu, Zhaohan Zhang, Shengchao Liu, Guoxin Ma, Yu Lan, Cong Wang, Chao Shen
| Challenge: | Existing work on reducing CoT generation in reasoning impairs the necessary information for deriving the correct answer. |
| Approach: | They propose a reasoning paradigm that takes CoT as a part of context to simplify the reasoning task for Large Language Models (LLMs). |
| Outcome: | The proposed framework reduces the generation length of LLMs, but its effectiveness hinges on the efficiency and reliability of the contextual CoT generation. |
Self-Training Elicits Concise Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Chain-of-thought reasoning has enabled large language models to use additional computation through intermediate tokens to solve complex tasks, but current models often generate more tokens than necessary to accomplish the task, incurring extraneous inference costs. |
| Approach: | They propose to fine-tune models with self-generated concise reasoning paths obtained by best-of-N sampling and few-shot conditioning in task-specific settings to elicit concise reasoning. |
| Outcome: | The proposed method reduces output tokens by 30% on GSM8K and MATH while maintaining average accuracy. |
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. |
Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot (2025.findings-emnlp)
Copied to clipboard
| Challenge: | In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs). |
| Approach: | They introduce CoT to exemplars of ICL to enhance the reasoning capability . however, it remains unclear whether CoT exemplar is still beneficial for recent, stronger models in such tasks. |
| Outcome: | The enhanced exemplars fail to improve the model’s reasoning performance, despite being constructed using answers from advanced models such as Qwen2.5-Max and DeepSeek-R1. |