Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Beyond Recall Saturation: Scaling Hard-Negative Reranker Training for Industrial Legal Retrieval

Yunhan Li, Mingjie Xie, Zeyang Shi, Gengshen Wu +1 more

Published

Oct 17, 2026

Citations

0

Trust level

Moderate

Usefulness score

65/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Oct 22, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Law Pairwise Preference

Should you rely on this paper?

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

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

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

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
65/100
Moderate-confidence candidate

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

If you are doing eval pipeline work, start here

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

Abstract

Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines. We show that, under a sufficiently large but practical candidate pool, embedding recall exhibits diminishing returns, motivating a closer examination of reranker quality. On Chinese legal retrieval benchmarks, embedding top-300 reaches a high-recall operating region, while relevant evidence may still be ranked below the output cutoff. We compare hard-negative strategies for reranker training, including embedding-mined, self-mined, and dynamic-negative variants, under aligned retrieval protocols that evaluate reranking after candidate retrieval. Among the evaluated staged configurations, an embedding-to-self-mined pipeline provides a favorable trade-off; additional dynamic stages do not improve all held-out metrics. The selected pipeline scales from a 0.6B to a 4B reranker. Relative to the native 4B reranker, the trained 4B Stage2 model improves reported metrics on the STARD and CSAID benchmarks and on an internal development set, and is preferred in 72.4\% of non-tied comparisons on 410 de-identified, reconstructed internal operational-query inputs in a latency-sensitive offline preference evaluation. These results support evaluating the retrieval and reranking stages separately when selecting an optimization target for industrial retrieval systems.

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

strong

Pairwise Preference

Directly usable for protocol triage.

"Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines."

Reported Metrics

strong

Recall

Useful for evaluation criteria comparison.

"We show that, under a sufficiently large but practical candidate pool, embedding recall exhibits diminishing returns, motivating a closer examination of reranker quality."

Benchmarks and datasets

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

Reported metrics

recall
Human feedback details
Uses human feedback
Yes
Feedback types
Pairwise Preference
Rater population
Not reported
Unit of annotation
Ranking
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines.

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

Key takeaways

  • Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines.
  • We show that, under a sufficiently large but practical candidate pool, embedding recall exhibits diminishing returns, motivating a closer examination of reranker quality.
  • On Chinese legal retrieval benchmarks, embedding top-300 reaches a high-recall operating region, while relevant evidence may still be ranked below the output cutoff.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • 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

Pairwise preference evaluation

Contribution summary

  • We show that, under a sufficiently large but practical candidate pool, embedding recall exhibits diminishing returns, motivating a closer examination of reranker quality.
  • On Chinese legal retrieval benchmarks, embedding top-300 reaches a high-recall operating region, while relevant evidence may still be ranked below the output cutoff.
  • Relative to the native 4B reranker, the trained 4B Stage2 model improves reported metrics on the STARD and CSAID benchmarks and on an internal development set, and is preferred in 72.4\% of non-tied comparisons on 410 de-identified,…

Why it matters for eval

  • On Chinese legal retrieval benchmarks, embedding top-300 reaches a high-recall operating region, while relevant evidence may still be ranked below the output cutoff.
  • Relative to the native 4B reranker, the trained 4B Stage2 model improves reported metrics on the STARD and CSAID benchmarks and on an internal development set, and is preferred in 72.4\% of non-tied comparisons on 410 de-identified,…

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Pairwise Preference

  • 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: recall