Research map / Large language models / Retrieval and knowledge
ToolQA: A Dataset for LLM Question Answering with External Tools
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| give the LLM external tools with ReAct instead of answering directly (ChatGPT) | gpt-3.5-turbo · ToolQA easy | success rate (%): 5.6 -> 36.8 | Helped |
| add chain-of-thought prompting to ChatGPT without tools | ChatGPT · ToolQA easy | success rate (%): 5.6 -> 5.1 | No clear effect |
| use ReAct with observation feedback instead of Chameleon's non-feedback planning | gpt-3.5-turbo · ToolQA easy | success rate (%): 10.6 -> 36.8 | Helped |
| switch ReAct backbone from GPT-3 to GPT-3.5 | ReAct · ToolQA easy | success rate (%): 43.1 -> 36.8 | Hurt |
| switch ReAct backbone from GPT-3 to GPT-3.5 | ReAct · ToolQA hard | success rate (%): 5.1 -> 8.2 | Helped |
| hard questions instead of easy questions (best method) | ReAct · ToolQA | success rate (%): 43.1 -> 8.2 | Hurt |
Closest papers by meaning
- RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content (NeurIPS 2024 · similarity 0.93)
- FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering (AAAI 2024 · similarity 0.91)
- Rethinking Generative Large Language Model Evaluation for Semantic Comprehension (ICML 2024 · similarity 0.90)
- SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs (ICLR 2024 · similarity 0.90)
- Explore What LLM Does Not Know in Complex Question Answering (AAAI 2025 · similarity 0.90)
- NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens (ICLR 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.