SHAPE Diagnoses LLM Math Reasoning via Semantic Spaces
SeoulNatlUniv · hf · 2026-09-01
Seoul National University presents SHAPE, a framework that analyzes chain-of-thought reasoning via semantic spaces and heuristics. The work aims to diagnose LLM performance in mathematical reasoning and improve post-training processes.
More from Research
- Building Non-LLM-as-a-Judge Verification for Context-Scoped AI — One_Stay_1385 · 2026-09-01
- Santa Fe Institute Hiring Postdoc on Thermodynamic Costs of Distributed Computation in Neural Networks and Brains — AnnaCiaunica · 2026-09-01
- Seoul National University Releases MineAmongUs: VLM Agents Learn to Lie in Embodied Social Settings — SeoulNatlUniv · 2026-09-01
- Naver Proposes Verification-Aware Training to Boost Speculative Decoding Draft Models — naver-ai · 2026-09-01
- Tsinghua researchers break 41-year record, prove Dijkstra is not optimal — jedisct1 · 2026-09-01
- Discussion: RL instills model behaviors independent of system prompts — voooooogel · 2026-09-01