Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Negative-Only Policy Optimization for One-Sided Verifiable Rewards

Jiacheng Xu, Shuo He, Fuxiang Zhang, Chaojie Wang +1 more

Published

Nov 12, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

35% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 12, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
0/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Reinforcement learning with verifiable rewards (RLVR) typically relies on a verifier that can reliably judge whether sampled solutions are correct. However, in many realistic settings, complete verification is generally unavailable, while cheap checks can only falsify failures. We formalize this regime as one-sided verifiability (OSV): verified negatives are reliable counterexamples, but verified positives are merely non-falsified candidates and may contain many false positives. This asymmetry makes standard RLVR unreliable, because reinforcing verified positives can directly reward shortcuts that pass partial checks. To address this issue, we propose Negative-Only Policy Optimization (NOPO), which treats verified positives as unlabeled and updates the policy only by suppressing trusted verified negatives. Specifically, NOPO combines a reference-relative negative suppression loss with a group-level adapter that scales each update by the proportion of non-falsified responses. Across unit-test, constraint-check, and LLM self-verifiers, NOPO improves pass@k over baselines on code, logic, and math benchmarks when oracle rewards are unavailable. These gains persist under inference-time scaling and cross-benchmark transfer.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Reinforcement learning with verifiable rewards (RLVR) typically relies on a verifier that can reliably judge whether sampled solutions are correct."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Reinforcement learning with verifiable rewards (RLVR) typically relies on a verifier that can reliably judge whether sampled solutions are correct."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Reinforcement learning with verifiable rewards (RLVR) typically relies on a verifier that can reliably judge whether sampled solutions are correct."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Reinforcement learning with verifiable rewards (RLVR) typically relies on a verifier that can reliably judge whether sampled solutions are correct."

Reported Metrics

partial

Pass@k

Useful for evaluation criteria comparison.

"Across unit-test, constraint-check, and LLM self-verifiers, NOPO improves pass@k over baselines on code, logic, and math benchmarks when oracle rewards are unavailable."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

pass@k
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
Math, Coding
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Reinforcement learning with verifiable rewards (RLVR) typically relies on a verifier that can reliably judge whether sampled solutions are correct.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Reinforcement learning with verifiable rewards (RLVR) typically relies on a verifier that can reliably judge whether sampled solutions are correct.
  • However, in many realistic settings, complete verification is generally unavailable, while cheap checks can only falsify failures.
  • We formalize this regime as one-sided verifiability (OSV): verified negatives are reliable counterexamples, but verified positives are merely non-falsified candidates and may contain many false positives.

Researcher actions

  • Compare this paper against others mentioning MATH.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

MATH Pass@k

Contribution summary

  • Reinforcement learning with verifiable rewards (RLVR) typically relies on a verifier that can reliably judge whether sampled solutions are correct.
  • However, in many realistic settings, complete verification is generally unavailable, while cheap checks can only falsify failures.

Why it matters for eval

  • Across unit-test, constraint-check, and LLM self-verifiers, NOPO improves pass@k over baselines on code, logic, and math benchmarks when oracle rewards are unavailable.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: pass@k