REVIEW 22 cited by
Self-Training Elicits Concise Reasoning in Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Chain-of-thought (CoT) reasoning has enabled large language models (LLMs) to utilize additional computation through intermediate tokens to solve complex tasks. However, we posit that typical reasoning traces contain many redundant tokens, incurring extraneous inference costs. Upon examination of the output distribution of current LLMs, we find evidence on their latent ability to reason more concisely, relative to their default behavior. To elicit this capability, we propose simple fine-tuning methods which leverage self-generated concise reasoning paths obtained by best-of-N sampling and few-shot conditioning, in task-specific settings. Our combined method achieves a 30% reduction in output tokens on average, across five model families on GSM8K and MATH, while maintaining average accuracy. By exploiting the fundamental stochasticity and in-context learning capabilities of LLMs, our self-training approach robustly elicits concise reasoning on a wide range of models, including those with extensive post-training. Code is available at https://github.com/TergelMunkhbat/concise-reasoning
Forward citations
Cited by 22 Pith papers
-
Are Large Reasoning Models Interruptible?
Interrupting large reasoning models or changing the problem mid-thought sharply degrades accuracy, with up to 60% drops and distinct failure modes: reasoning leakage, panic, and self-doubt.
-
Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model
Suppressing 'thinking tokens' in a 1.5B reasoning model preserves accuracy while cutting tokens, and the proposed DuP-PO RL method improves both accuracy and efficiency over GRPO.
-
Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement
Large reasoning models already contain the ability to reason concisely; steering their internal activations or rewarding brevity can cut reasoning length by up to half without hurting accuracy.
-
How Far Are We from Optimal Reasoning Efficiency?
The authors define a reasoning efficiency frontier and a gap metric (REG), then train models with REO-RL to shrink the gap by at least 50% with only small accuracy losses.
-
PixelThink: Towards Efficient Chain-of-Pixel Reasoning
A soft token-budget penalty driven by task difficulty and model confidence roughly halves the reasoning tokens used by segmentation MLLMs while slightly improving mask accuracy on ReasonSeg-derived benchmarks.
-
Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning
Self-Route uses hidden-layer representations from a brief pre-inference plan to route each question to either short or long chain-of-thought, cutting tokens by 30-55% with under 2% accuracy loss.
-
Efficient Long CoT Reasoning in Small Language Models
Binary cutting with on-policy validation prunes redundant chain-of-thought steps in teacher traces, letting 7B models keep most long-CoT accuracy while generating fewer tokens.
-
Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards
An adaptive length-penalty reward for RL-trained LLMs reduces reasoning length by over 50% with small accuracy loss by automatically tightening and relaxing the penalty based on the model's current accuracy.
-
VeriThinker: Learning to Verify Makes Reasoning Model Efficient
VeriThinker shows that fine-tuning a reasoning model only on a solution-verification task reduces chain-of-thought length on MATH500 and AIME by 20-45% while preserving or slightly improving accuracy.
-
Not All Tokens Are What You Need In Thinking
A method that scores each chain-of-thought token by answer-conditioned perplexity and trains models on the compressed traces preserves or improves reasoning accuracy with significantly fewer tokens.
-
Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?
Standard pointwise rerankers beat reasoning-based pointwise rerankers under identical training, and removing the reasoning process at inference partially recovers the gap.
-
TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling
TrimR uses a lightweight verifier to detect redundant thoughts in reasoning models and truncates them, cutting runtime by up to 70% without retraining.
-
Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
An adaptive, difficulty-aware length reward for RL training makes large reasoning models produce shorter chains of thought while matching or improving math accuracy.
-
LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
LISA replaces standard attention with linear attention plus indexer-selected sparse attention, claiming O(nM) inference cost and accuracy gains, but the complexity analysis ignores the indexer's full-context scoring.
-
CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs
A training-free and label-free detector of cyclic hidden-state patterns triggers early exit during chain-of-thought reasoning, reducing token length while mostly preserving or improving accuracy.
-
Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty
Reward shaping with a powered length penalty makes LLMs answer easy questions with far fewer tokens while preserving or slightly improving accuracy on hard math benchmarks.
-
Can Past Experience Accelerate LLM Reasoning?
LLMs can cut reasoning compute by up to 56% on similar questions when memory of past correct solutions is combined with adaptive early stopping, though the benchmark is small and synthetic.
-
Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
ACPO uses special fast/slow thinking tokens and an online length-budget reward to make LLM math reasoning shorter and difficulty-adaptive, with modest accuracy loss.
-
A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning
Ten-epoch SFT then GRPO raises AIME/MATH-500 accuracy while reducing solution length, achieving 8th place on AIMO's private set.
-
PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models
The paper reports that a concise optimized prompt reduces reasoning tokens by up to 87.5% while roughly preserving accuracy on GSM8K, SVAMP, and MATH-500.
-
Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
Suppressing "Wait"-like reflection tokens at decode time reduces reasoning token counts by 27-51% across five R1-style model families, with mixed accuracy effects.
-
Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
A comprehensive review that categorizes methods for shortening and adaptively triggering chain-of-thought reasoning in large language models.
Discussion (0). Sign in to comment.