Probe with Participation Trophies: Random-Reward RL as a Probe of LLM Capability
cs.CL
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/mynotwo/rl-random-prob
Terminology
Sources
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Demystifying Reinforcement Learning Post-Training of Language Models
- Training Verifiers to Solve Math Word Problems
- Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
- Linear representations in language models can change dramatically over a conversation
- Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction
- On the Compressibility of Quantized Large Language Models
- 2 OLMo 2 Furious
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering