| Challenge: | Large Language Models have achieved impressive performance across a range of tasks, but further gains require more than scaling up model sizes or training data. |
| Approach: | They propose a method that gradually reduces the number of thought tokens . this method allows models to internalize more abstract reasoning processes . |
| Outcome: | The proposed framework preserves the benefits of token-level reasoning while reducing computational cost. |
Similar Papers
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. |
SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to continuous-space reasoning focus on hard token decoding and suffer from catastrophic forgetting. |
| Approach: | They propose a method that generates instance-specific soft thought tokens as the initial chain of thoughts and maps them into the LLM’s representation space via a trainable projection module. |
| Outcome: | The proposed method improves LLM reasoning performance through supervised, parameter-efficient fine-tuning. |
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. |
Self-SoftCoT: A Self-Consistent Framework via Position-Aware Latent Space Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing Continuous reasoning approaches rely on external auxiliary models, resulting in complex deployment and fractured inference pipelines. |
| Approach: | They propose a self-contained framework that enables a frozen LLM to internally generate and consume latent thoughts without external assistants. |
| Outcome: | The proposed framework outperforms SoftCoT models on five reasoning benchmarks. |
Coherence boosting: When your pretrained language model is not paying enough attention (2022.acl-long)
Copied to clipboard
| Challenge: | Long-range semantic coherence remains a challenge in automatic language generation and understanding. |
| Approach: | They propose a procedure that increases a model’s focus on a long context by distributional analyses of generated ordinary text and dialog responses. |
| Outcome: | The proposed procedure increases the model's focus on a long context. |
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. |
Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, yet their autoregressive generation paradigm makes it computationally prohibitive to explore diverse reasoning paths. |
| Approach: | They propose a framework that combines diffusion-based generation with autoregressive evaluation to efficiently generate diverse intermediate reasoning thoughts and employ LLMs as evaluators to assess and select candidates based on their plausibility and correctness. |
| Outcome: | The proposed framework improves inference efficiency while maintaining competitive or superior reasoning accuracy. |
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models (2024.acl-long)
Copied to clipboard
Changyu Chen, Xiting Wang, Ting-En Lin, Ang Lv, Yuchuan Wu, Xin Gao, Ji-Rong Wen, Rui Yan, Yongbin Li
| Challenge: | Despite the advances in large language models, they still face difficulties with multi-step reasoning tasks. |
| Approach: | They propose a method that randomly masks certain tokens within the chain of thought to improve model accuracy by 5% over standard supervised fine-tuning. |
| Outcome: | The proposed method improves accuracy and accuracy by 5% over standard fine-tuning with a few codes modified. |
Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Instruction-fine-tuned large language models (LLMs) under 14B parameters underperform on NLU tasks . we explore a framework to improve the NLU capabilities of LLMs . |
| Approach: | They propose to use Proximal Policy Optimization to improve NLU capabilities . they frame NLU as a reinforcement learning environment and optimize for reward signals . |
| Outcome: | The proposed framework outperforms supervised fine-tuning on GLUE and superGLUE tasks. |
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. |