Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs

Zara Siddique, Irtaza Khalid, Liam D. Turner, Luis Espinosa-Anke · Mar 7, 2025 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this paper page

Coverage: Stale

Use this page to decide whether the paper is strong enough to influence an eval design. It summarizes the abstract plus available structured metadata. If the signal is thin, use it as background context and compare it against stronger hub pages before making protocol choices.

Best use

Background context only

Metadata: Stale

Trust level

Low

Signals: Stale

What still needs checking

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Signal confidence: 0.25

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.

Use caution before copying this protocol

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

Extraction flags indicate low-signal or possible false-positive protocol mapping.
Extraction confidence is 0.25 (below strong-reference threshold).
No explicit evaluation mode was extracted from available metadata.

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

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

Background context only.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

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

What This Page Found In The Paper

Each field below shows whether the signal looked explicit, partial, or missing in the available metadata. Use this to judge what is safe to trust directly and what still needs full-paper validation.

Human Feedback Types

missing

None explicit

Confidence: Low Not found

No explicit feedback protocol extracted.

Evidence snippet: 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

Confidence: Low Not found

Validate eval design from full paper text.

Evidence snippet: 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

Confidence: Low Not found

No explicit QC controls found.

Evidence snippet: 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

Confidence: Low Direct evidence

Useful for quick benchmark comparison.

Evidence snippet: 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

Confidence: Low Not found

No metric anchors detected.

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

Rater Population

missing

Unknown

Confidence: Low Not found

Rater source not explicitly reported.

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

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: General
Signal basis: Structured extraction plus abstract evidence.

Evaluation Lens

Evaluation modes:
Agentic eval: None
Quality controls: Not reported
Signal confidence: 0.25
Known cautions: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

MMLUBBQ

Reported Metrics

No metric terms were extracted from the available abstract.

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

Research Summary

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

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Gap: Evaluation mode is explicit

No clear evaluation mode extracted.
Gap: Quality control reporting appears

No calibration/adjudication/IAA control explicitly detected.
Pass: Benchmark or dataset anchors are present

Detected: MMLU, BBQ
Gap: Metric reporting is present

No metric terms extracted.

Related Papers

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

No related papers found for this item yet.

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.

Self-Service

Post a Job

Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.

Create Account & Post a Job

Managed Service

For Large Projects

Done-for-You

We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.

Learn About Managed Service

For Freelancers

Join as an AI Trainer

Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.

Join Now