23 citations · 23 across the 6 of their papers we have counts for
3 papers · 1 filter
Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised
Harsh Kumar, Tanmay Shailesh Joshi, Rahul Maity +1
Code models write Python when the prompt does not say which language to use. We ask a mechanistic question about that habit: is it produced by a small, findable group of components…
PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training
Harsh Kumar, Rahul Maity, Tanmay Joshi +4
Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential attack surface. W…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…