AI Paper Atlas

Research map / Benchmarks / NarrativeQA

NarrativeQA leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NarrativeQA. Best F1: 65 (Zero-Shot AgentInstruct, ICML 2024).

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.

NarrativeQA · F1

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

#F1 ↑MethodPaperTopic
165Zero-Shot AgentInstruct
Llama-2-70b-chat
Agent Instructs Large Language Models to be General Zero-Shot Reasoners
ICML 2024 · Ablation Studies table
Language, safety and interpretability
260InstructRetro 43B
Retro 48B
InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
ICML 2024 · Table: short-form QA
Retrieval and knowledge
337.4HTSIR
GPT-4o mini
Improving Long-Context Summarization with Multi-Granularity Retrieval Optimization
AAAI 2026 · Table 3
Retrieval and knowledge
431.43ComoRAG
GPT-4o-mini
ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning
AAAI 2026 · Table 1
Retrieval and knowledge
527.84Psi-RAG (summative abstract)
Llama-3.3-70B
Hierarchical Abstract Tree for Cross-Document Retrieval Augmented Generation
ICML 2026 · Table 4
Human and embodied modeling
626.9FilM-7B
Mistral-7B-Instruct-v0.2
Make Your LLM Fully Utilize the Context
NeurIPS 2024 · Real-world long-context tasks
Retrieval and knowledge
725.9HippoRAG 2
Llama-3.3-70B-Instruct
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
ICML 2025 · QA performance table
Retrieval and knowledge
825.26CoA (8k)
text-bison
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
NeurIPS 2024 · Overall results table
Retrieval and knowledge
918.5BART + Unlimiformer
BART-base
Unlimiformer: Long-Range Transformers with Unlimited Length Input
NeurIPS 2023 · Table: other tasks
Attention and transformers
1017.1ICLMIn-Context Pretraining: Language Modeling Beyond Document Boundaries
ICLR 2024 · SCROLL table
Language, safety and interpretability

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