AI Paper Atlas

Research map / Benchmarks / WebQSP

WebQSP leaderboard

22 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on WebQSP. Best F1: 87.7 (RAR (Llama-3.1-8B + GPT-4o-mini), TPAMI 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

WebQSP · F1

15 papers, each with its best reported number for its own method; higher is better.

#F1 ↑MethodPaperTopic
187.7RAR (Llama-3.1-8B + GPT-4o-mini)Reason-Align-Respond: Aligning LLM Reasoning With Knowledge Graphs for KGQA
TPAMI 2026 · Table 1
Retrieval and knowledge
284.24FM-KBQA
Llama-2-7B
Promoting Knowledge Base Question Answering by Directing LLMs to Generate Task-relevant Logical Forms
AAAI 2025 · Table 1
Retrieval and knowledge
383.4KBQA-R1
Llama-3.1-8B
KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
ICML 2026 · Table 4
Retrieval and knowledge
481.4DP
GPT-4o
Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs
NeurIPS 2025 · DP performance with various LL
Retrieval and knowledge
581.3EoG
Llama-3.1-8B
Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling
ICLR 2026 · Table 1
Retrieval and knowledge
681.3BoG
Llama-3.1-8B
Backjump-on-Graph: Empowering Large Language Models with Reinforced Retrospective Exploration for Agentic Knowledge Graph Reasoning
ICML 2026 · Table 1
Retrieval and knowledge
781.24CoD (ours)
Llama2-7B
Enhancing LLMs for Knowledge Base Question Answering by Chain-of-Decomposition
ICLR 2026 · Table 1
Retrieval and knowledge
881.2AMAR
LLaMA2-7B
Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation
AAAI 2025 · Main results table
Retrieval and knowledge
978.8DecAF (DPR + FiD-3B)
FiD-3B
DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases
ICLR 2023 · Table 1
Visual question answering
1074.8SCR (GPT-4o-mini)
GPT-4o-mini
Stepwise Contrastive Reasoning for Retrieval-Augmented Generation over Knowledge Graphs
AAAI 2026 · Table 1
Retrieval and knowledge
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

WebQSP · Hits@1

14 papers, each with its best reported number for its own method; higher is better.

#Hits@1 ↑MethodPaperTopic
192.7BoG
Llama-3.1-8B
Backjump-on-Graph: Empowering Large Language Models with Reinforced Retrospective Exploration for Agentic Knowledge Graph Reasoning
ICML 2026 · Table 1
Retrieval and knowledge
291.2PARoG
GPT-4
Plan-Answer-Refine-on-Graph: Structured Planning and Self-Refinement for Large Language Model Reasoning on Knowledge Graphs
ICLR 2026 · Table 1
Retrieval and knowledge
388.8EPERM
LLaMA2-Chat-7B
EPERM: An Evidence Path Enhanced Reasoning Model for Knowledge Graph Question and Answering
AAAI 2025 · Main results table
Retrieval and knowledge
487.34FM-KBQA
Llama-2-7B
Promoting Knowledge Base Question Answering by Directing LLMs to Generate Task-relevant Logical Forms
AAAI 2025 · Table 1
Retrieval and knowledge
587.3PoG
GPT-4
Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
NeurIPS 2024 · Table: Performance comparison
Retrieval and knowledge
686.54CoD (ours)
Llama2-7B
Enhancing LLMs for Knowledge Base Question Answering by Chain-of-Decomposition
ICLR 2026 · Table 1
Retrieval and knowledge
785.7RoG
LLaMA2-Chat-7B
Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
ICLR 2024 · Main results table
Retrieval and knowledge
884.3AMAR
LLaMA2-7B
Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation
AAAI 2025 · Main results table
Retrieval and knowledge
983.8LightPROF (LLaMa3-8B)
LLaMa3-8B
LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph
AAAI 2025 · Table: Performance comparison
Retrieval and knowledge
1082.1DecAF (DPR + FiD-3B)
FiD-3B
DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases
ICLR 2023 · Table 1
Visual question answering
4 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.