Reading vs. Writing a Near-Oracle Internal Verifier: How RL Design Determines Whether a Correctness Probe Is Safe

#artificial intelligence Preprint Aug 2026

HSRM: Hidden-State Reward Models for Test-Time Verification

HSRM is introduced, a lightweight hidden-state reward model that verifies candidate solutions by directly reading the generator's internal representations rather than re-processing its text, providing an efficient alternative to text-only verification by reusing representations already computed during generation.

Xianzhi Li, Xiao-Dan Zhu · 0 citations

Preprint Aug 2026

How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models

An observability ladder is introduced that holds each completed run fixed and varies only what a reader inspects to judge whether the answer is correct: the response, a self-summary the model writes from the trace, the trace itself, and internal signals, each with and without the prompt.

A. Algaba, Francesca Carlon, Lynn Delcon et al. · 0 citations

Review Aug 2026

Judging Is Not Enumerating: Silent Omissions in LLM-Authored Acceptable Sets

This work measures the capability that role assumes and finds it lacking under the protocol the role is usually deployed with, one-shot greedy authoring with no test-time reasoning.

Wen-Hui Chen, Jian-Lin Chen, Zi-Yao Lin et al. · 1 citation

#artificial intelligence Preprint Aug 2026

Reinforcement Learning on Benign Facts Amplifies Leakage of Memorized Private Data

Reinforcement learning with verifiable rewards (RLVR) is deployed to make models better at reasoning tasks, but its side effect on what models will divulge is under studied. Here we show that RLVR on facts increases extraction of personally identifiable information (PII) the instruct model had already memorized. We fir...

Renfei Zhang, Niloofar Mireshghallah · 1 citation

Jul 2026

Reference Traces for Auditing Invisible Weight Updates and Guiding Exact-Budget Protection

This work asks what a high-precision reference trace establishes before a low-precision run, and investigates whether aggregate forecasts can reflect shared time rather than source-specific transfer.

Zekai Shang · arXiv.org · 0 citations

Preprint Jul 2026

The Knowing-Saying Gap: When Probes See Errors that Confidence Misses

Probe-based monitoring is a necessary complement to verbalised confidence, but no single intervention dominates, and the deployable answer is model-aware, error-type-aware routing.

Jyotin Goel, Ipshita Bandyopadhyay, Justin Shenk · 0 citations