Chain of Thought

Prompt Engineering: Lilian Weng's Comprehensive Survey

Lilian Weng's canonical reference on prompt engineering techniques — zero-shot, few-shot, chain-of-thought, self-consistency, tree-of-thoughts, and more — grounded in research papers. Still the most comprehensive single-author survey of the space.

PAL: Program-aided Language Models

PAL prompts LLMs to generate Python programs as intermediate reasoning steps, then delegates actual computation to an interpreter, outperforming chain-of-thought on math and symbolic tasks. It neatly separates what LLMs are good at (translating problems to code) from what they're bad at (arithmetic).

Scaling Instruction-Finetuned Language Models

The FLAN-T5 and Flan-PaLM paper (2022) showing that instruction finetuning across 1.8K tasks improves performance on zero-shot, few-shot, and chain-of-thought prompting across multiple model families. Established instruction finetuning as a general-purpose method and released Flan-T5 checkpoints that shaped the open-source LLM ecosystem.

STaR: Bootstrapping Reasoning With Reasoning

Large Language Models Can Self-Improve

Huang et al. (2022) show that LLMs can bootstrap their own reasoning ability by generating chain-of-thought rationales, filtering with self-consistency majority vote, and finetuning on the high-confidence outputs — no human labels needed. A clean demonstration that LLMs can improve themselves without supervised signal.