Language models lack systematicity in generating and updating hypotheses
cs.LG
Submitted: 2026-05-07
Updated: 2026-11-07
Terminology
Sources
- Artificial intelligence for science: The easy and hard problems
- Concept Generalization in Humans and Large Language Models: Insights from the Number Game
- Transformers as Meta-Learners for Implicit Neural Representations
- Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context
- Learning without training: The implicit dynamics of in-context learning
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- NVIDIA Nemotron 3: Efficient and Open Intelligence
- On Language Models' Sensitivity to Suspicious Coincidences
- Uncovering mesa-optimization algorithms in Transformers
- From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
- An Explanation of In-context Learning as Implicit Bayesian Inference
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis