A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Yu Wang, Shiwan Zhao, Zhihu Wang, et al.
SCoT improves LLM reasoning by first eliciting a problem-solving strategy before generating Chain-of-Thought steps, achieving significant gains on reasoning benchmarks.
Chengshuai Zhao, Zhen Tan, Pingchuan Ma, et al.
Proposes a data distribution lens to understand when and why Chain-of-Thought reasoning succeeds or fails, revealing it as a brittle mirage beyond training distributions.
Jundong Xu, Hao Fei, Liangming Pan, et al.
Proposes SymbCoT, a fully LLM-based framework integrating symbolic expressions and logic rules with Chain-of-Thought prompting to enhance logical reasoning.
J. Kirchner, Yining Chen, Harri Edwards, et al.
Proposes legibility training via a Prover-Verifier Game to make LLM chain-of-thought reasoning easier for humans to verify, improving trust in model outputs.
Unknown
PIR optimizes chain-of-thought data by pruning low-importance reasoning steps, improving accuracy and reducing token usage.
Unknown
Proposes Direct Judgement Preference Optimization to enhance LLM judges via Chain-of-Thought Critique, Standard Judgement, and Response Deduction for rating, comparison, and classification.
Unknown
NuminaMath introduces a massive 860k problem-solution dataset with chain-of-thought traces to boost LLM mathematical reasoning, winning the 1st AIMO Progress Prize.
Unknown
MAmmoTH-VL introduces a cost-effective pipeline to create a 12M multimodal instruction-tuning dataset with chain-of-thought reasoning, achieving state-of-the-art performance on diverse benchmarks.
Unknown
MAmmoTH introduces a series of LLMs trained on MathInstruct, a dataset combining chain-of-thought and program-of-thought rationales for general math problem-solving.
Unknown
Explores scaling instruction fine-tuning by increasing tasks, model size, and incorporating chain-of-thought data to improve language model performance.
Unknown
This paper explores methods to transfer chain-of-thought reasoning capabilities from large to small language models via knowledge distillation.
Jason Wei, Xuezhi Wang, Dale Schuurmans, et al.
Showed that including step-by-step reasoning examples in prompts dramatically improves LLM performance on arithmetic, commonsense, and symbolic reasoning tasks — an emergent ability appearing only at scale.