Mor Geva

Mor Geva on Hugging Face Daily Papers: 23 papers, 3 in the top 3 of their day, 362 upvotes.

  1. Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth 14 upvotes, #25 of 2026-05-26
  2. Hallucinations Undermine Trust; Metacognition is a Way Forward 22 upvotes, #3 of 2026-05-05
  3. Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs 70 upvotes, #2 of 2026-03-11
  4. From Directions to Regions: Decomposing Activations in Language Models via Local Geometry 3 upvotes, #41 of 2026-02-11
  5. Rethinking Selective Knowledge Distillation 22 upvotes, #22 of 2026-02-03
  6. Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context 8 upvotes, #18 of 2025-10-08
  7. LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations 19 upvotes, #4 of 2025-09-04
  8. Universal Jailbreak Suffixes Are Strong Attention Hijackers 5 upvotes, #26 of 2025-06-18
  9. Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization 6 upvotes, #27 of 2025-06-13
  10. Precise In-Parameter Concept Erasure in Large Language Models 1 upvotes, #54 of 2025-05-29
  11. Open Problems in Mechanistic Interpretability 16 upvotes, #5 of 2025-01-29
  12. Enhancing Automated Interpretability with Output-Centric Feature Descriptions 10 upvotes, #13 of 2025-01-15
  13. CoverBench: A Challenging Benchmark for Complex Claim Verification 11 upvotes, #8 of 2024-08-07
  14. From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty 7 upvotes, #14 of 2024-07-10
  15. From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP 4 upvotes, #21 of 2024-06-21
  16. Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces 3 upvotes, #8 of 2024-06-20
  17. Estimating Knowledge in Large Language Models Without Generating a Single Token 6 upvotes, #21 of 2024-06-19
  18. Do Large Language Models Latently Perform Multi-Hop Reasoning? 28 upvotes, #6 of 2024-02-27
  19. Patchscope: A Unifying Framework for Inspecting Hidden Representations of Language Models 20 upvotes, #9 of 2024-01-12
  20. Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers 13 upvotes, #7 of 2024-01-10
  21. In-Context Learning Creates Task Vectors 43 upvotes, #1 of 2023-10-25
  22. Evaluating the Ripple Effects of Knowledge Editing in Language Models 13 upvotes, #7 of 2023-07-25
  23. The Hidden Language of Diffusion Models 5 upvotes, #10 of 2023-06-02

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.