AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information

Mehran Kazemi, Quan Yuan, Deepti Bhatia, Najoung Kim, Xin Xu, Vaiva Imbrasaite, Deepak Ramachandran

NeurIPS 2023 · Large language models › Language, safety and interpretability · approach: Text generation and evaluation metrics · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
increase reasoning depth from 1 to 3finetuned BERT and T5 · BoardgameQAaccuracyHurt
few-shot prompting instead of tuningPaLM 62B/540B · BoardgameQAconflict F1Hurt
scale PaLM from 62B to 540BPaLM few-shot · BoardgameQAaccuracyImproved
increase conflict probability from none to high (0.0, 0.2, 0.5, 0.8)all models · BoardgameQAaccuracyHurt
shift conflicts toward Type1 (p=0.2 vs 0.8 Type1)all models · BoardgameQAaccuracyImproved
bias dataset toward a single conflict typetuned models · BoardgameQAaccuracyImproved
increase required missing knowledge (p_MissInfo 0.2 to 0.8)finetuned models · BoardgameQAaccuracyHurt
increase required missing knowledge (p_MissInfo 0.2 to 0.8)prompt-tuned and few-shot PaLM · BoardgameQAaccuracyNo clear effect
add 1 distractor per steptuned models · BoardgameQAaccuracyNo clear effect
add 2 distractors per steptuned models · BoardgameQAaccuracyHurt
increase distractorsfew-shot PaLM · BoardgameQAaccuracyHurt
binary (proved/disproved) version of the datasetT5 · BoardgameQA depth 2accuracyImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy