Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making

Abhinaba Basu, Pavan Chakraborty

Published

Mar 19, 2026

Citations

0

Trust level

Low

Usefulness score

40/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Mar 19, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Coding Rubric Rating

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

Background context only.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

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

Human feedback signal
Detected
From extracted signals
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
40/100
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

Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized. We introduce ICE-Guard, a framework applying intervention consistency testing to detect three types of spurious feature reliance: demographic (name/race swaps), authority (credential/prestige swaps), and framing (positive/negative restatements). Across 3,000 vignettes spanning 10 high-stakes domains, we evaluate 11 LLMs from 8 families and find that (1) authority bias (mean 5.8%) and framing bias (5.0%) substantially exceed demographic bias (2.2%), challenging the field's narrow focus on demographics; (2) bias concentrates in specific domains -- finance shows 22.6% authority bias while criminal justice shows only 2.8%; (3) structured decomposition, where the LLM extracts features and a deterministic rubric decides, reduces flip rates by up to 100% (median 49% across 9 models). We demonstrate an ICE-guided detect-diagnose-mitigate-verify loop achieving cumulative 78% bias reduction via iterative prompt patching. Validation against real COMPAS recidivism data shows COMPAS-derived flip rates exceed pooled synthetic rates, suggesting our benchmark provides a conservative estimate of real-world bias. Code and data are publicly available.

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

partial

Rubric Rating

Directly usable for protocol triage.

"Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized."

Benchmarks and datasets

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

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Rubric Rating
Rater population
Not reported
Unit of annotation
Multi Dim Rubric (inferred)
Expertise required
Coding
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized.

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

Key takeaways

  • Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized.
  • We introduce ICE-Guard, a framework applying intervention consistency testing to detect three types of spurious feature reliance: demographic (name/race swaps), authority (credential/prestige swaps), and framing (positive/negative restatements).
  • Across 3,000 vignettes spanning 10 high-stakes domains, we evaluate 11 LLMs from 8 families and find that (1) authority bias (mean 5.8%) and framing bias (5.0%) substantially exceed demographic bias (2.2%), challenging the field's narrow focus on demographics; (2) bias concentrates in specific domains -- finance shows 22.6% authority bias while criminal justice shows only 2.8%; (3) structured decomposition, where the LLM extracts features and a deterministic rubric decides, reduces flip rates by up to 100% (median 49% across 9 models).

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

Rubric rating evaluation

Contribution summary

  • We introduce ICE-Guard, a framework applying intervention consistency testing to detect three types of spurious feature reliance: demographic (name/race swaps), authority (credential/prestige swaps), and framing (positive/negative…
  • Across 3,000 vignettes spanning 10 high-stakes domains, we evaluate 11 LLMs from 8 families and find that (1) authority bias (mean 5.8%) and framing bias (5.0%) substantially exceed demographic bias (2.2%), challenging the field's narrow…
  • We demonstrate an ICE-guided detect-diagnose-mitigate-verify loop achieving cumulative 78% bias reduction via iterative prompt patching.

Why it matters for eval

  • Validation against real COMPAS recidivism data shows COMPAS-derived flip rates exceed pooled synthetic rates, suggesting our benchmark provides a conservative estimate of real-world bias.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Rubric Rating

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • 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

    No metric terms extracted.