AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Syllogism-Inspired TableQA: Evidentialization Makes Decomposition Reasoning and Answer Verification More Reliable

Zhe Zhang, Lili Bai, Chaopeng Guo, Jie Song

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 0 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
use SIRV instead of TIDE (joint DP&Agent)TableQA with GPT-3.5 · WTQexact match accuracy: 75.00 -> 77.89Improved
use SIRV instead of TIDE (joint DP&Agent)TableQA with GPT-3.5 · TabFactexact match accuracy: 89.82 -> 91.85Improved
use SIRV-Agent instead of TIDE-AgentAgent mode · WTQexact match accuracy: 68.72 -> 73.96Improved
use SIRV-DP instead of Norm-DPDP mode · WTQexact match accuracy: 66.99 -> 67.38Improved
add evidential answer verification (SIRV-AV) (ablation)SIRV · WTQ joint DP&Agentexact match accuracy: 74.31 -> 77.89Improved
add evidence-centered decomposition reasoning (SIRV-DR) (ablation)SIRV · WTQ Agent modeexact match accuracy: 68.01 -> 73.96Improved
add evidence-centered decomposition reasoning (SIRV-DR) (ablation)SIRV · TabFact joint DP&Agentexact match accuracy: 87.26 -> 91.85Improved
add SIRV-DR and SIRV-AV to Agent mode (vs standard CoT) (ablation)SIRV-Agent · WTQ jointexact match accuracy: 71.91 -> 77.89Improved
use SIRV-DR/AV only in DP while Agent uses standard CoT (ablation)SIRV · WTQ Agent modeexact match accuracy: 67.38 vs 67.38 (DP unchanged)No clear effect
replace self-correction prompting with evidential verification (ablation)SIRV-AV · WTQ and TabFactanswer correction rate: 47.39 -> 55.71 (mean)Improved
increase candidate answers from 1 to 5 in each mode (ablation)SIRV majority voting · WTQexact match accuracy: 70.07 -> 77.89Improved
use 5 DP and 5 Agent answers instead of 3:5 on TabFact (ablation)SIRV majority voting · TabFactexact match accuracy: 91.85 (3:5) vs 91.21 (5:5)Hurt

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