Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs

Zara Siddique, Irtaza Khalid, Liam D. Turner, Luis Espinosa-Anke

Published

Mar 7, 2025

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

25% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Mar 28, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

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

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
Weak or implicit
Validate from full paper
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

We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes. We compute 8 steering vectors, each corresponding to a different social bias axis, such as age, gender, or race, on a training subset of the BBQ dataset and compare the effectiveness of these to 3 additional bias mitigation methods across 4 datasets. When optimized on the BBQ dataset, our individually tuned steering vectors achieve average improvements of 12.8% on BBQ, 8.3% on CLEAR-Bias, and 1% on StereoSet, and show improvements over prompting and Self-Debias in all cases, and improvements over fine-tuning in 12 out of 17 evaluations. In addition, steering vectors showed the lowest impact on MMLU scores of the four bias mitigation methods tested. The work presents the first systematic investigation of steering vectors for bias mitigation, and we demonstrate that they are a powerful and computationally efficient strategy for reducing bias in LLMs, with broader implications for enhancing AI safety.

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.

"We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes."

Quality Controls

missing

Not reported

No explicit QC controls found.

"We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes."

Benchmarks / Datasets

partial

MMLU, BBQ

Useful for quick benchmark comparison.

"We compute 8 steering vectors, each corresponding to a different social bias axis, such as age, gender, or race, on a training subset of the BBQ dataset and compare the effectiveness of these to 3 additional bias mitigation methods across 4 datasets."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes."

Benchmarks and datasets

MMLUBBQ

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
General
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

We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes.

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

Key takeaways

  • We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes.
  • We compute 8 steering vectors, each corresponding to a different social bias axis, such as age, gender, or race, on a training subset of the BBQ dataset and compare the effectiveness of these to 3 additional bias mitigation methods across 4 datasets.
  • When optimized on the BBQ dataset, our individually tuned steering vectors achieve average improvements of 12.8% on BBQ, 8.3% on CLEAR-Bias, and 1% on StereoSet, and show improvements over prompting and Self-Debias in all cases, and improvements over fine-tuning in 12 out of 17 evaluations.

Researcher actions

  • Compare this paper against others mentioning MMLU.
  • 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

MMLU

Contribution summary

  • We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes.
  • When optimized on the BBQ dataset, our individually tuned steering vectors achieve average improvements of 12.8% on BBQ, 8.3% on CLEAR-Bias, and 1% on StereoSet, and show improvements over prompting and Self-Debias in all cases, and…
  • The work presents the first systematic investigation of steering vectors for bias mitigation, and we demonstrate that they are a powerful and computationally efficient strategy for reducing bias in LLMs, with broader implications for…

Why it matters for eval

  • When optimized on the BBQ dataset, our individually tuned steering vectors achieve average improvements of 12.8% on BBQ, 8.3% on CLEAR-Bias, and 1% on StereoSet, and show improvements over prompting and Self-Debias in all cases, and…
  • The work presents the first systematic investigation of steering vectors for bias mitigation, and we demonstrate that they are a powerful and computationally efficient strategy for reducing bias in LLMs, with broader implications for…

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • 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

    Detected: MMLU, BBQ

  • Metric reporting is present

    No metric terms extracted.