arXiv subjects

Dylan Jayabahu

Publications and source records attributed to Dylan Jayabahu.

2 recordsLinked to original sources

arXiv2026

The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes

A truth probe fitted where truthful reporting and a task's prescribed action coincide cannot distinguish those targets from its fitting labels alone. We call this failure of semantic identification perfect aliasing. In a controlled binary reporting game, truth and prescribed-action probes fitted on compliant contexts solve the same optimization. On rival contexts their labels are complements, forcing their AUROCs to sum to one; this identity holds across 751 cell-layer pairs to floating-point precision. We separate prescribed output symbols from semantic action using randomized codebooks, then separate truth from prescribed action by fitting on mixed compliant and rival contexts. For a reward-trained Gemma-2-9B policy that answers falsely on all evaluated rival trials, the conventional probe scores $0.006 \pm 0.005$ AUROC across three training seeds, while mixed-fit probes score $1.000$ on the same held-out activations. Mixed fitting uses more training examples and access to labelled rival contexts, so this comparison establishes linear recoverability rather than isolating the benefit of decorrelation. We also show that two compliant-fit probes, both perfect in-distribution, score $0.080$ and $0.986$ on the same rival activations. The findings concern what a probe measures: they do not establish preserved functional belief, causal use of the recovered direction, or a deployable deception detector. Code and aggregate results accompany the paper.

cs.LG↗

arXiv2026

The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning

Reasoning models do not stop when they know the answer. On DeepSeek-R1-Distill-Qwen-7B the chain of thought runs about twice as long as the model's own answer probability takes to settle, and how much of that excess is removable varies from problem to problem, so a global length penalty cannot take it out. We take it out by internalizing a causal interpretability finding into the weights. The mechanism is a halt vector: a difference-of-means direction at layer 18 of this model whose steering strength controls how long it thinks, while a replicated value axis does nothing. Installing that intervention in the weights is harder than it looks. Maximizing the scalar projection onto the direction corrupts the off-axis dimensions a frozen downstream reader depends on, and generation gets longer instead of shorter; what works is reconstructing the whole steered activation with those dimensions pinned to their natural values. Fit from 24 problems and no reinforcement learning, the halt removes about a quarter of the thinking at held accuracy across five unseen benchmarks, and the cut tracks each problem's own removable slack at 0.70. It also closes a non-termination pathology that grows with difficulty and that a decoding-time confidence hook makes worse. We do not claim to beat a well-tuned length penalty or decoding-time early exit on the raw trade-off; the contribution is how the halt is obtained.

cs.LG↗