madaan / self-refineLinks
LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.
☆763Updated last year
Alternatives and similar repositories for self-refine
Users that are interested in self-refine are comparing it to the libraries listed below
Sorting:
- [ACL 2023] Reasoning with Language Model Prompting: A Survey☆991Updated 7 months ago
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them☆536Updated last year
- ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate☆497Updated 7 months ago
- Data and code for FreshLLMs (https://arxiv.org/abs/2310.03214)☆380Updated 3 weeks ago
- Forward-Looking Active REtrieval-augmented generation (FLARE)☆661Updated 2 years ago
- Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"☆316Updated last year
- This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.☆561Updated last year
- PaL: Program-Aided Language Models (ICML 2023)☆518Updated 2 years ago
- An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]☆372Updated last year
- Repo for paper "Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration"☆347Updated last year
- [NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models☆672Updated 5 months ago
- MAD: The first work to explore Multi-Agent Debate with Large Language Models :D☆480Updated this week
- [NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents☆446Updated last year
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆768Updated 2 years ago
- ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels …☆283Updated 2 years ago
- [TMLR] Cumulative Reasoning With Large Language Models (https://arxiv.org/abs/2308.04371)☆307Updated 4 months ago
- A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.☆385Updated 2 years ago
- FireAct: Toward Language Agent Fine-tuning☆287Updated 2 years ago
- ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings - NeurIPS 2023 (oral)☆266Updated last year
- FacTool: Factuality Detection in Generative AI☆900Updated last year
- List of language agents based on paper "Cognitive Architectures for Language Agents"☆1,102Updated 11 months ago
- ☆1,331Updated last year
- Data and Code for Program of Thoughts [TMLR 2023]☆300Updated last year
- Code for Quiet-STaR☆742Updated last year
- [EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627☆504Updated last year
- Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".☆658Updated 2 weeks ago
- [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the dive…☆973Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆562Updated 10 months ago
- RewardBench: the first evaluation tool for reward models.☆670Updated 6 months ago
- Aligning Large Language Models with Human: A Survey☆740Updated 2 years ago