Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts

Jiuheng Lin, Cong Jiang, Zirui Wu, Jiarui Sun, Yansong Feng · Oct 10, 2025 · Citations: 0

Automatic Metrics Coding Human Eval
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Low trust

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

Best use

Background context only

What to verify

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

Evidence quality

Low

Derived from extracted protocol signals and abstract evidence.

Abstract

Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While it may improve accuracy, we observe it often degrades reasoning quality such as logical consistency. Existing solutions to supervise reasoning, such as large-scale Process Reward Models (PRMs), are prohibitively expensive. To address this, we propose CLARity, a cost-effective RL framework that enhances reasoning quality using only a small, general-purpose LLM. CLARity integrates a consistency-aware reward mechanism with a 2-stage refine-then-monitor training pipeline to enhance reasoning consistency, and a dynamic data reformulation strategy to to better exploit limited data. Experiments demonstrate that CLARity improves response consistency by 16.5% and accuracy by 7.5% over baselines. Human evaluations further confirm holistic improvements in coherence and professionalism. Thus, CLARity offers a generalizable solution that enables smaller models to effectively guide expert models by reasoning consistency. Our code is open sourced at: https://github.com/Infinite-set/CLARity

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • The available metadata is too thin to trust this as a primary source.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

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.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

The available metadata is too thin to trust this as a primary source.

Trust level

Low

Usefulness score

37/100 • Low

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

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

Usefulness for eval research

Adjacent candidate

Extraction confidence 45%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

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.

"Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs)."

Evaluation Modes

partial

Human Eval, Automatic Metrics

Includes extracted eval setup.

"Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs)."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs)."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs)."

Reported Metrics

partial

Accuracy, Coherence

Useful for evaluation criteria comparison.

"While it may improve accuracy, we observe it often degrades reasoning quality such as logical consistency."

Rater Population

partial

Domain Experts

Helpful for staffing comparability.

"Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs)."

Human Feedback Details

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Domain Experts
  • Expertise required: Coding

Evaluation Details

  • Evaluation modes: Human Eval, Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Evidence quality: Low
  • Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

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

Reported Metrics

accuracycoherence

Research Brief

Metadata summary

Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs).

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

Key Takeaways

  • Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs).
  • However, standard outcome-based reinforcement learning (RL) on MCQs is risky.
  • While it may improve accuracy, we observe it often degrades reasoning quality such as logical consistency.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Human evaluation, 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.

Research Summary

Contribution Summary

  • While it may improve accuracy, we observe it often degrades reasoning quality such as logical consistency.
  • To address this, we propose CLARity, a cost-effective RL framework that enhances reasoning quality using only a small, general-purpose LLM.
  • Human evaluations further confirm holistic improvements in coherence and professionalism.

Why It Matters For Eval

  • Human evaluations further confirm holistic improvements in coherence and professionalism.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Human Eval, Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: accuracy, coherence

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.