pith. sign in

arxiv: 2412.11664 · v1 · pith:ZEKRMJALnew · submitted 2024-12-16 · 💻 cs.CL · cs.LG

C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness

classification 💻 cs.CL cs.LG
keywords answergeneratedllmslongershortertextbfgeneratinglength
0
0 comments X
read the original abstract

Generating Chain-of-Thought (CoT) before deriving the answer can effectively improve the reasoning capabilities of large language models (LLMs) and significantly improve the accuracy of the generated answer. However, in most cases, the length of the generated CoT is much longer than the desired final answer, which results in additional decoding costs. Furthermore, existing research has discovered that shortening the reasoning steps in CoT, even while preserving the key information, diminishes LLMs' abilities. These phenomena make it difficult to use LLMs and CoT in many real-world applications that only require the final answer and are sensitive to latency, such as search and recommendation. To reduce the costs of model decoding and shorten the length of the generated CoT, this paper presents $\textbf{C}$onditioned $\textbf{C}$ompressed $\textbf{C}$hain-of-$\textbf{T}$hought (C3oT), a CoT compression framework that involves a compressor to compress an original longer CoT into a shorter CoT while maintaining key information and interpretability, a conditioned training method to train LLMs with both longer CoT and shorter CoT simultaneously to learn the corresponding relationships between them, and a conditioned inference method to gain the reasoning ability learned from longer CoT by generating shorter CoT. We conduct experiments over four datasets from arithmetic and commonsense scenarios, showing that the proposed method is capable of compressing the length of generated CoT by up to more than 50% without compromising its effectiveness.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost

    cs.AI 2026-05 conditional novelty 7.0

    Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.

  2. TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models

    cs.AI 2026-04 unverdicted novelty 7.0

    TrigReason matches large reasoning model accuracy on math and science benchmarks by delegating most steps to small models and intervening selectively on three triggers, cutting latency by 43.9% and cost by 73.3%.

  3. Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

    cs.AI 2026-05 unverdicted novelty 6.0

    SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.

  4. LightThinker++: From Reasoning Compression to Memory Management

    cs.CL 2026-04 unverdicted novelty 6.0

    LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.

  5. Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models

    cs.CL 2026-01 unverdicted novelty 6.0

    NCoTS treats chain-of-thought reasoning as a search problem and uses a dual-factor heuristic to find paths that are over 3.5% more accurate and 22% shorter on benchmarks.

  6. When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation

    cs.CL 2026-06 unverdicted novelty 5.0

    Empirical sweep disentangles importance criterion, restructuring level, and compression budget in CoT distillation, revealing granularity governs criterion utility, domain-dependent restructuring effects, and that tra...

  7. CROP: Token-Efficient Reasoning in Large Language Models via Regularized Prompt Optimization

    cs.CL 2026-04 unverdicted novelty 5.0

    CROP achieves 80.6% token reduction on GSM8K, LogiQA and BIG-Bench Hard with only nominal accuracy decline by regularizing automatic prompt optimization with response-length feedback.

  8. Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

    cs.CL 2025-03 accept novelty 5.0

    A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.