Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Reliable Financial Named Entity Recognition under Domain Shift

Zihao Zheng, Baichuan Li, Junyi Yao, Jiayu Long

Published

Aug 20, 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

Aug 20, 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

Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the input distribution changes. We study confidence estimation and selective prediction for financial named entity recognition (NER) on a three-tier stress test spanning SEC filings, financial news, and general-topic social media as an extreme out-of-domain condition. We evaluate a BERT tagger and LoRA-tuned Qwen2.5-0.5B/1.5B models using five inference-time confidence signals, three training seeds, and bootstrap intervals. Confidence rankings themselves change under distribution shift: whole-output probability is the strongest in-domain error detector but deteriorates out of domain, whereas entity-span probability and self-consistency are more robust; self-consistency is also better calibrated without post-hoc fitting. Abstention reduces sentence error from 34.3% to below 2% on the highest-confidence 40% of in-domain inputs and remains useful on financial news, but recovers no usefully large clean subset under the extreme social-media shift. These results motivate a staged deployment strategy that detects severe distribution shift upstream before applying prediction-level confidence gating.

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.

"Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the input distribution changes."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the input distribution changes."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the input distribution changes."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the input distribution changes."

Reported Metrics

partial

F1

Useful for evaluation criteria comparison.

"Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the input distribution changes."

Benchmarks and datasets

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

Reported metrics

f1
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Ranking (inferred)
Expertise required
General
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

Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the input distribution changes.

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

Key takeaways

  • Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the input distribution changes.
  • We study confidence estimation and selective prediction for financial named entity recognition (NER) on a three-tier stress test spanning SEC filings, financial news, and general-topic social media as an extreme out-of-domain condition.
  • We evaluate a BERT tagger and LoRA-tuned Qwen2.5-0.5B/1.5B models using five inference-time confidence signals, three training seeds, and bootstrap intervals.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • 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

F1

Contribution summary

  • Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores do not indicate which predictions remain safe to automate when the…
  • We evaluate a BERT tagger and LoRA-tuned Qwen2.5-0.5B/1.5B models using five inference-time confidence signals, three training seeds, and bootstrap intervals.
  • Abstention reduces sentence error from 34.3% to below 2% on the highest-confidence 40% of in-domain inputs and remains useful on financial news, but recovers no usefully large clean subset under the extreme social-media shift.

Why it matters for eval

  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

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: f1