Skip to content
← Back to explorer

Document Reconstruction Unlocks Scalable Long-Context RLVR

Yao Xiao, Lei Wang, Yue Deng, Guanzheng Chen, Ziqi Jin, Jung-jae Kim, Xiaoli Li, Roy Ka-wei Lee, Lidong Bing · Feb 9, 2026 · Citations: 0

Automatic Metrics Coding Rubric Rating
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 2, 2026, 7:07 AM

Stale

Extraction refreshed

Apr 13, 2026, 6:39 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.80

Abstract

Reinforcement Learning with Verifiable Rewards~(RLVR) has become a prominent paradigm to enhance the capabilities (i.e.\ long-context) of Large Language Models~(LLMs). However, it often relies on gold-standard answers or explicit evaluation rubrics provided by powerful teacher models or human experts, which are costly and time-consuming. In this work, we investigate unsupervised approaches to enhance the long-context capabilities of LLMs, eliminating the need for heavy human annotations or teacher models' supervision. Specifically, we first replace a few paragraphs with special placeholders in a long document. LLMs are trained through reinforcement learning to reconstruct the document by correctly identifying and sequencing missing paragraphs from a set of candidate options. This training paradigm enables the model to capture global narrative coherence, significantly boosting long-context performance. We validate the effectiveness of our method on two widely used benchmarks, RULER and LongBench~v2. While acquiring noticeable gains on RULER, it can also achieve a reasonable improvement on LongBench~v2 without any manually curated long-context QA data. Furthermore, we conduct extensive ablation studies to analyze the impact of reward design, data curation strategies, training schemes, and data scaling effects on model performance. We publicly release our code, data, and models.

HFEPX Relevance Assessment

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Best use

Secondary protocol comparison source

Use if you need

A benchmark-and-metrics comparison anchor.

Main weakness

No major weakness surfaced.

Trust level

High

Eval-Fit Score

65/100 • Medium

Useful as a secondary reference; validate protocol details against neighboring papers.

Human Feedback Signal

Detected

Evaluation Signal

Detected

HFEPX Fit

Moderate-confidence candidate

Extraction confidence: High

If you are doing eval pipeline work, start here:

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

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

strong

Rubric Rating

Confidence: High Source: Persisted extraction evidenced

Directly usable for protocol triage.

Evidence snippet: Reinforcement Learning with Verifiable Rewards~(RLVR) has become a prominent paradigm to enhance the capabilities (i.e.\ long-context) of Large Language Models~(LLMs).

Evaluation Modes

strong

Automatic Metrics

Confidence: High Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Reinforcement Learning with Verifiable Rewards~(RLVR) has become a prominent paradigm to enhance the capabilities (i.e.\ long-context) of Large Language Models~(LLMs).

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Reinforcement Learning with Verifiable Rewards~(RLVR) has become a prominent paradigm to enhance the capabilities (i.e.\ long-context) of Large Language Models~(LLMs).

Benchmarks / Datasets

strong

LongBench

Confidence: High Source: Persisted extraction evidenced

Useful for quick benchmark comparison.

Evidence snippet: We validate the effectiveness of our method on two widely used benchmarks, RULER and LongBench~v2.

Reported Metrics

strong

Coherence

Confidence: High Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: This training paradigm enables the model to capture global narrative coherence, significantly boosting long-context performance.

Rater Population

strong

Domain Experts

Confidence: High Source: Persisted extraction evidenced

Helpful for staffing comparability.

Evidence snippet: However, it often relies on gold-standard answers or explicit evaluation rubrics provided by powerful teacher models or human experts, which are costly and time-consuming.

Human Data Lens

  • Uses human feedback: Yes
  • Feedback types: Rubric Rating
  • Rater population: Domain Experts
  • Unit of annotation: Multi Dim Rubric
  • Expertise required: Coding
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.80
  • Flags: None

Protocol And Measurement Signals

Benchmarks / Datasets

LongBench

Reported Metrics

coherence

Research Brief

Deterministic synthesis

However, it often relies on gold-standard answers or explicit evaluation rubrics provided by powerful teacher models or human experts, which are costly and time-consuming. HFEPX signals include Rubric Rating, Automatic Metrics with confidence 0.80. Updated from current HFEPX corpus.

Generated Apr 13, 2026, 6:39 AM · Grounded in abstract + metadata only

Key Takeaways

  • However, it often relies on gold-standard answers or explicit evaluation rubrics provided by powerful teacher models or human experts, which are costly and time-consuming.
  • In this work, we investigate unsupervised approaches to enhance the long-context capabilities of LLMs, eliminating the need for heavy human annotations or teacher models'…

Researcher Actions

  • Compare its human-feedback setup against pairwise and rubric hubs.
  • Cross-check benchmark overlap: LongBench.
  • Validate metric comparability (coherence).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Extraction confidence is probabilistic and should be validated for critical decisions.

Research Summary

Contribution Summary

  • However, it often relies on gold-standard answers or explicit evaluation rubrics provided by powerful teacher models or human experts, which are costly and time-consuming.
  • In this work, we investigate unsupervised approaches to enhance the long-context capabilities of LLMs, eliminating the need for heavy human annotations or teacher models' supervision.
  • We validate the effectiveness of our method on two widely used benchmarks, RULER and LongBench~v2.

Why It Matters For Eval

  • However, it often relies on gold-standard answers or explicit evaluation rubrics provided by powerful teacher models or human experts, which are costly and time-consuming.
  • In this work, we investigate unsupervised approaches to enhance the long-context capabilities of LLMs, eliminating the need for heavy human annotations or teacher models' supervision.

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Rubric Rating

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: LongBench

  • Pass: Metric reporting is present

    Detected: coherence

Related Papers

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

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote