AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering

An-Yang Ji, Jun-Peng Jiang, De-Chuan Zhan, Han-Jia Ye

ICML 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
add semantic hints (target, task type, feature descriptions) (ablation)Qwen3-Instruct agentic · Single-Pointaccuracy: 0.43 -> 0.56Improved
add semantic hints (ablation)DeepSeek-V3.2 agentic · Treatment Effecttrend accuracy: 0.57 -> 0.68Improved
add semantic hints (ablation)GPT-5.2 agentic · Single-Pointaccuracy: 0.60 -> 0.64Improved
add semantic hints (ablation)GPT-5.2 agentic · Ranking and FilteringF1: 0.38 -> 0.48Improved
add semantic hints (ablation)Gemini 3 Flash agentic · Decision Makingdecision accuracy: 0.65 -> 0.61Hurt
add semantic hints (ablation)GPT-5.2 agentic · Decision Makingdecision accuracy: 0.55 -> 0.53Hurt
add semantic hints (ablation)Gemini 3 Flash agentic · Ranking and FilteringF1: 0.58 -> 0.57No clear effect
replace LLM-only agent with predict-only tabular ensemble given gold profile (ablation)Gemini 3 Flash agentic · Single-Pointaccuracy: 0.66 -> 0.76Improved
replace LLM-only agent with predict-only tabular ensemble given gold profile (ablation)Gemini 3 Flash agentic · Decision Makingdecision accuracy: 0.65 -> 0.72Improved
replace LLM-only agent with predict-only tabular ensemble given gold profile (ablation)Gemini 3 Flash agentic · Treatment Effecttrend accuracy: 0.65 -> 0.69Improved
use agentic code execution instead of text-based reasoningGPT-5.2 · Treatment Effecttrend accuracy: 0.51 -> 0.65Improved
use agentic code execution instead of text-based reasoningQwen3-Instruct · Single-Pointaccuracy: 0.57 -> 0.43Hurt

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