AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in LLMs

Soyeon Kim, Jindong Wang, Xing Xie, Steven Euijong Whang

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Explanatory and multiple-choice QA benchmarks

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
require correct time references in addition to correct answer (AT vs A)8 LLMs on TDBench · TDBench temporal alignment, Wikipediaaccuracy: 56.9 -> 35.2 (average A -> AT)Hurt
add Chain-of-Thought or Time-CoT prompting instead of RAG on multi-hop questions (ablation)GPT-4 · TDBench multi-hopaccuracy: 67.2 -> 92.4 (CoT), 93.9 (Time-CoT)Improved
add RAG with retrieved Wikipedia passages (ablation)GPT-4 · TDBench multi-hopaccuracy: 67.2 -> 35.4Hurt
add RAG with retrieved Wikipedia passages (ablation)GPT-3.5 · TDBench multi-hopaccuracy: 63.1 -> 71.2Improved
add CoT or Time-CoT prompting (ablation)GPT-3.5 · TDBench multi-hopaccuracy: 63.1 -> 39.4 (CoT), 15.2 (Time-CoT)Hurt
add Time-CoT prompting (ablation)GPT-4o · TDBench multi-hopaccuracy: 79.3 -> 95.5Improved
Time-CoT versus plain CoT (ablation)multi-hop prompting · TDBench multi-hopaccuracyNo clear effect
add RAG with retrieved Wikipedia passages (ablation)Gemma2-27B · TDBench multi-hopaccuracy: 77.8 -> 40.9Hurt
build TSQA pairs from SQL with answers grounded in database instead of manual authoringTDBench · agreement with manual verificationF1: 0.97 (alignment), 0.88 (reasoning), 0.91 (multi-hop)Improved

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