Probe-derived value signal as a free process reward
Fit a linear TD probe on hidden states to get a per-step value estimate, take its step-to-step change as a reward prediction error, and use that as the scoring signal for best-of-n or search at inference, so no separate reward model is run.
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Fit a linear TD probe on hidden states to get a per-step value estimate, take its step-to-step change as a reward prediction error, and use that as the scoring signal for best-of-n or search at inference, so no separate reward model is run. Filed by the drafting stage from Sparse Reward Subsystem in Large Language Models (2602.00986) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: MATH500 accuracy under search guided by the probe signal against greedy, random and implicit-PRM guidance; causal ablation of value neurons against random, magnitude and Wanda baselines across layers; transfer of value probes across datasets and models reported. Single 7B model family for the ablation.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.