technique
β-Hindsight control
techniqueactiveprovisional
-hindsight-control-c7757456·1 events·first seen 21d agoAliases: β-Hindsight control
Co-occurring entities
More like this (12)
Hindsight Experience ReplayAI controlclosed-loop controlExpert Blindness Effectshared controlPredicting Future Behaviors in Reasoning Models Enables Better SteeringRetrospective Memorycounterfactual reasoningpredictor-corrector methodsChain-of-Thought Fine-TuningVisual Verification Enables Inference-time Steering and Autonomous Policy Improvementinference-time behavioural unlearning
Recent events (1)
Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering
The paper introduces the Gumbel Machine, a modular framework for generating counterfactual text that improves student writing while preserving similarity to the original. Central to the approach is β-Hindsight control, a controlled decoding algorithm that uses Gumbel noise as a tunable similarity mechanism during LLM generation. Experiments on student writing datasets show the method produces outputs that are both rubric-consistent and close to the reference text. The approach is positioned as more flexible and practically applicable than prior domain-specific counterfactual generation methods.