Lune

EMNLP Findings2023

ExpNote: Black-box Large Language Models are better Task Solvers with Experience Notebook

Wangtao Sun, Xuanqing Yu, Shizhu He, Jun Zhao, Kang Liu

Abstract

Black-box Large Language Models (LLMs) have shown great power in solving various tasks and are considered general problem solvers. However, LLMs still fail in many specific tasks although understand the task instruction. In this paper, we focus on the problem of boosting the ability of black-box LLMs to solve downstream tasks. We propose Exp-Note, an automated framework to help LLMs better adapt to unfamiliar tasks through reflecting and noting experiences from training data and retrieving them from external memory during testing. We evaluate ExpNote on multiple tasks and the experimental results demonstrate that the proposed method significantly improves the performance of black-box LLMs. The data and code are available at https://github.com/forangel2014/ExpNote.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Self-Refine: Iterative Refinement with Self-Feedback cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Reflexion: language agents with verbal reinforcement learning cites Self-Refine: Iterative Refinement with Self-Feedback
  • Reflexion: language agents with verbal reinforcement learning cites Toolformer: Language Models Can Teach Themselves to Use Tools
  • Reflexion: language agents with verbal reinforcement learning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • ItD: Large Language Models Can Teach Themselves Induction through Deduction cites LoRA: Low-Rank Adaptation of Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. ItD: Large Language Models Can Teach Themselves Induction through DeductionWangtao Sun, Haotian Xu, Xuanqing Yu, Pei Chen et al.ACL 2024

Builds on14

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  3. Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
  4. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  5. Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations

Related papers

  1. ExpeTrans: LLMs Are Experiential Transfer LearnersJinglong Gao, Xiao Ding, Lingxiao Zou, Bibo Cai et al.ACL 2025
  2. Tool Learning in the Wild: Empowering Language Models as Automatic Tool AgentsZhengliang Shi, Shen Gao, Lingyong Yan, Yue Feng et al.WWW 2025 · 59 citations
  3. Self-Evolving GPT: A Lifelong Autonomous Experiential LearnerJinglong Gao, Xiao Ding, Yiming Cui, Jianbai Zhao et al.ACL 2024 · 4 citations
  4. RefTool: Reference-Guided Tool Creation for Knowledge-Intensive ReasoningXiao Liu, Da Yin, Zirui Wu, Yansong FengICLR 2026 · 2 citations
  5. Learning to Reason and Memorize with Self-NotesJack Lanchantin, Shubham Toshniwal, Jason Weston, Arthur Szlam et al.NeurIPS 2023 · 45 citations
Dusk over the sea between two cliffs drawn in fine vertical lines