ML Research Wiki / Benchmarks / Question Answering / Bamboogle

Bamboogle

Question Answering Benchmark

Performance Over Time

📊 Showing 9 results | 📏 Metric: Accuracy

Top Performing Models

Rank Model Paper Accuracy Date Code
1 ReST meets ReAct (PaLM 2-L + Google Search) ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent 76.10 2023-12-15 -
2 MCR (code-davinci-002) + Google Search Answering Questions by Meta-Reasoning over Multiple Chains of Thought 66.50 2023-04-25 📦 oriyor/reasoning-on-cots
3 RALM (LLaMA2-13B + Google Search) Making Retrieval-Augmented Language Models Robust to Irrelevant Context 62.70 2023-10-02 📦 ruc-nlpir/flashrag 📦 oriyor/ret-robust
4 Self-ask (GPT-3; davinci-002) + Google Search Measuring and Narrowing the Compositionality Gap in Language Models 60.00 2022-10-07 📦 ofirpress/self-ask
5 Self-ask (GPT-3; davinci-002) Measuring and Narrowing the Compositionality Gap in Language Models 57.60 2022-10-07 📦 ofirpress/self-ask
6 Chain-of-Thought (GPT-3; davinci-002) Measuring and Narrowing the Compositionality Gap in Language Models 46.40 2022-10-07 📦 ofirpress/self-ask
7 FireAct FireAct: Toward Language Agent Fine-tuning 44.00 2023-10-09 -
8 Direct Prompting (GPT-3; davinci-002) Measuring and Narrowing the Compositionality Gap in Language Models 17.60 2022-10-07 📦 ofirpress/self-ask
9 Google Search Measuring and Narrowing the Compositionality Gap in Language Models 0.00 2022-10-07 📦 ofirpress/self-ask

All Papers (9)

ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent

2023
ReST meets ReAct (PaLM 2-L + Google Search)
oriyor/reasoning-on-cots
ruc-nlpir/flashrag oriyor/ret-robust

Measuring and Narrowing the Compositionality Gap in Language Models

2022
Self-ask (GPT-3; davinci-002) + Google Search
ofirpress/self-ask
ofirpress/self-ask
ofirpress/self-ask
ofirpress/self-ask
ofirpress/self-ask