Author

Esther Xin

h-index 1 View on Semantic Scholar

4 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Does Chain-of-Thought Reliance Follow a Scaling Law?Larger Models Follow Their Steps More, Independent of Post-Training

Monitoring a model's chain of thought (CoT) is useful for safety only if the final answer depends on the written steps. Prior measurements use natural tasks where true reasoning is unknown. We measure it against an exact ground truth on a synthetic box-swap task where every intermediate state is known. We replace one s...

Esther Xin · 0 citations

#machine learning Preprint Sep 2026

When a Data Artifact Isn't a Shortcut: Causal Auditing of Synthetic RLVR Corpora

Several recent pipelines build RLVR training data by masking a span of real corpus text and asking a language model to invent plausible wrong answers around it. The correct option is therefore genuine human prose; every distractor is synthetic. Correctness and provenance become entangled, and a policy could in principl...

Esther Xin · 0 citations

#machine learning Preprint Sep 2026

Are Verifier Errors Independent Within a GRPO Group? Evidence from Qwen2.5 Rollouts

These findings motivate prompt- and answer-form-aware analyses of verifier noise rather than characterizations based solely onaggregate error rates.

Esther Xin · 1 citation

#machine learning Preprint Sep 2026

Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR

This work applies metamorphic testing to the verifier rather than the model, generating certified equivalent answer variants, that is, rewrites that preserve mathematical meaning by construction, so that any rejection is a provable false negative needing no human adjudication.

Esther Xin · 3 citations · ⚡1