Harry Mayne

1. Negation Neglect: When models fail to learn negations in training
   2026/05/13 by Harry Mayne, Lev McKinney, Jan Dubiński +3 · 8 voices · 1 citation
   #cs.CL #cs.AI #cs.LG
2. LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages
   2024/06/10 by Andrew M. Bean, Simi Hellsten, Bean, Andrew M. +13 · 10 citations
   Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques
3. Can sparse autoencoders be used to decompose and interpret steering vectors?
   2024/11/13 by Harry Mayne, Yushi Yang, Mayne, Harry +3 · 8 citations
   Computer Science · Engineering · #Advanced Vision and Imaging #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Human Pose and Action Recognition #Machine Learning (cs.LG) #Vehicle Dynamics and Control Systems
4. Measuring what Matters: Construct Validity in Large Language Model Benchmarks
   2025/11/03 by Andrew M. Bean, Bean, Andrew M., Angelika Romanou +78 · 10 citations
   Computer Science · Medicine · Social Sciences · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Healthcare and Education #Computation and Language (cs.CL) #Computational and Text Analysis Methods #FOS: Computer and information sciences #Topic Modeling
5. Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values
   2026/07/15 by Jan Betley, Johannes Treutlein, Jan Dubiński +5 · 4 voices
   #cs.LG #cs.AI #cs.CR