AI Paper Atlas

Research map / Benchmarks / TriviaQA

TriviaQA leaderboard

86 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on TriviaQA. Best accuracy: 91 (WebSeer (Web Search), ICLR 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.

TriviaQA · accuracy

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

#accuracy ↑MethodPaperTopic
191WebSeer (Web Search)
Qwen2.5-14B
WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection
ICLR 2026 · Table 1
Human-AI and goal-conditioned
289.6RAG-DDR (2 rounds)
Llama3-8B
RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
ICLR 2025 · Table 1
Retrieval and knowledge
387.46DSLA [25%]
Llama2-7B
On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving
ICML 2025 · Table 1
Attention and transformers
484.9AugCon
Llama3-70B-Instruct
Automatically Generating Numerous Context-Driven SFT Data for LLMs Across Diverse Granularity
AAAI 2025 · Automatic evaluation table
Instruction and fine-tuning
583.63Dustin-HDustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding
ICML 2026 · Table 3
Attention and transformers
680.65MemGen-GRPO
Qwen3-8B
MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
ICLR 2026 · Table 1
LLM agents
778.5InstructRAG-FT
Llama-3-Instruct 8B
InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
ICLR 2025 · Main results table
Retrieval and knowledge
875.26LAR
Qwen3-32B
Latent Action Reparameterization for Efficient Agent Inference
NeurIPS 2026 · text
Human-AI and goal-conditioned
974.24Verifier-8x7B + Drafter-7B
Mistral-7B drafter; Mixtral-8x7B verifier
Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
ICLR 2025 · Main results table
Retrieval and knowledge
1073.7KVLink5
Llama-3.2-3B
KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
NeurIPS 2025 · Main results table
Reasoning and chain of thought
22 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

TriviaQA · EM

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

#EM ↑MethodPaperTopic
186.2WET (Ours)
Llama-3.1-8B
WET: Mitigating World-Conditioned Knowledge Conflicts via World Entropy Tethering
ICML 2026 · Table 1
Language, safety and interpretability
281.02CF-RAG
Llama-3-8B-Instruct
Counterfactual Reasoning for Retrieval-Augmented Generation
ICLR 2026 · Table 1
Retrieval and knowledge
380.2SkillOrchestra+
Qwen2.5-3B
SkillOrchestra: Learning to Route Agents via Skill Transfer
NeurIPS 2026 · Table 1
LLM agents
478.3InstructRetro 43B
Retro 48B
InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
ICML 2024 · Table: short-form QA
Retrieval and knowledge
576GPT-3 + Contriever top-10
Code-Davinci-002
Prompting GPT-3 To Be Reliable
ICLR 2023 · Table 9
Language, safety and interpretability
674.3GenRead (FiD-xl) merged with retrieved docs
InstructGPT
Generate rather than Retrieve: Large Language Models are Strong Context Generators
ICLR 2023 · Table 3
Retrieval and knowledge
774.14xRAG
Mixtral-8x7b
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
NeurIPS 2024 · Table 1
Human and embodied modeling
873LazyAttention
Tulu3-Block-FT (Llama-3.1-8B)
LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding
ICML 2026 · Table 2
Retrieval and knowledge
972.5Ours (DPR initialization, T5 large)
T5 large
Distilling Knowledge from Reader to Retriever for Question Answering
ICLR 2021 · Table 2
Knowledge distillation
1071.4EMDR² (MSS retriever, MSS reader)
T5-base reader; dual-encoder retriever
End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering
NeurIPS 2021 · Main results table
Molecules and proteins
19 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

TriviaQA · F1

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

#F1 ↑MethodPaperTopic
186.8WET (Ours)
Llama-3.1-8B
WET: Mitigating World-Conditioned Knowledge Conflicts via World Entropy Tethering
ICML 2026 · Table 1
Language, safety and interpretability
284.5SAIN SpanBERT
SpanBERT
Semantics-Aware Inferential Network for Natural Language Understanding
AAAI 2021 · Table 2
Language, safety and interpretability
381.7CRITIC
ChatGPT (gpt-3.5-turbo)
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
ICLR 2024 · Table 1
Agents, code and math
475.84Diffuser
RoBERTa
Diffuser: Efficient Transformers with Multi-Hop Attention Diffusion for Long Sequences
AAAI 2023 · Question answering table
Attention and transformers
573.29Block-Skim Training
BERT-base
Block-Skim: Efficient Question Answering for Transformer
AAAI 2022 · Table: validation F1 and FLOPs
Attention and transformers
673.2LLaMA2-70B-chat + Activation Decoding
LLaMA2-70B-chat
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
ICML 2024 · Table: Open-ended generation r
Language, safety and interpretability
771.93Graph-R1
Qwen2.5-7B-Instruct
Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
ICML 2026 · Table 1
Retrieval and knowledge
870DECOR
Qwen3-8B-Instruct
DECOR: Learning to Decompose and Collaborate in Deep Search via Multi-Agent Reinforcement Learning
ICML 2026 · Table 1
Cooperative multi-agent RL
968.9HAS-QA (MAX Ans. Span)HAS-QA: Hierarchical Answer Spans Model for Open-Domain Question Answering
AAAI 2019 · Table 2
Visual question answering
1068.15Memory+ (1T)
Llama3 8B
Memory Layers at Scale
ICML 2025 · 8B results table
RNNs and normalization
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

TriviaQA · AUROC

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

#AUROC ↑MethodPaperTopic
10.866Semantic density
Mistral-7B
Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space
NeurIPS 2024 · Table 1
Language, safety and interpretability
20.86Diversity-steered sampling
LLaDA 8B-Instruct
Efficient semantic uncertainty quantification in language models via diversity-steered sampling
NeurIPS 2025 · Table: AUROC of SE
Language, safety and interpretability
30.845SE_SDLG
OPT-13b
Improving Uncertainty Estimation through Semantically Diverse Language Generation
ICLR 2025 · Table 1
Language, safety and interpretability
40.841PRO
Gemma-7B
Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models
AAAI 2026 · Table 1
Language, safety and interpretability
50.84KLE(K_heat)
Llama 2 70B Chat
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
NeurIPS 2024 · Table 1
Language, safety and interpretability
60.83Semantic entropy
OPT-30B
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
ICLR 2023 · Table 2
Language, safety and interpretability
70.818Probe(AVG)
Gemma3-12B
Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models
AAAI 2026 · Table 1
Language, safety and interpretability
80.817GLU
Gemma3-12B
Integrating Local and Global Entropy for Uncertainty Quantification in LLMs
NeurIPS 2026 · Table 1
Language, safety and interpretability
90.808FLUEFLUE: Streamlined Uncertainty Estimation for Large Language Models
AAAI 2025 · Table 1
Language, safety and interpretability
100.8Llama3-70B base + LACIE
Llama3-70B base
LACIE: Listener-Aware Finetuning for Calibration in Large Language Models
NeurIPS 2024 · Table 1
Retrieval and knowledge
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.