Category

Factuality: RL environments and AI benchmarks

AI benchmarks
25
Shares entries with
0 categories

Snapshot 2026-10-11. How categories are built · Where the data comes from

In short

What are RL environments for factuality?
A simulated workplace where an AI agent practises a task (a code repository, a browser, business software) and an automatic grader scores each attempt. Labs train on thousands of these attempts. Bought to improve models.

Only benchmarks use the Factuality tag: the RL environment directories file their vendors under other categories. Browse all RL environments.

AI benchmarks 25

None confirmed yet.

25 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. AA-Omniscience
  2. Beyond Questions
  3. Finetuning with Scientific Data Increases Hallucinations
  4. GPF-LiveNews
  5. HalluScore
  6. ClaimDB
  7. ReMMD
  8. BenHalluEval
  9. Cited but Not Verified
  10. CommunityFact
  11. Correction Suppression Benchmark
  12. Counter Turing Test
  13. HalluWorld
  14. Knowledge-Intensive Video Generation
  15. Rethinking Evaluation for LLM Hallucination Detection
  16. Verified Misguidance
  17. AdversaRiskQA
  18. Multimodal Claim Extraction for Fact-Checking
  19. Right Knowledge
  20. VELI5
  21. Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking
  22. EditPropBench
  23. RW-Post
  24. What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness
  25. Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking

Next: pick another domain. Tags come from the RL Research daily scrape, canonicalized nightly.