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 page

Low trust

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Low

Derived from extracted protocol signals and abstract evidence.

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.

Abstract-only analysis — low confidence

All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.

This paper looks adjacent to evaluation work, but not like a strong protocol reference.
The available metadata is too thin to trust this as a primary source.
The abstract does not clearly describe the evaluation setup.

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

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.

Best use

Background context only

Use if you need

Background context only.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Trust level

Low

Usefulness 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

Usefulness for eval research

Adjacent candidate

Extraction confidence 25%

If you are doing eval pipeline work, start here:

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

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."

Human Feedback Details

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

Evaluation Details

Evaluation modes:
Agentic eval: None
Quality controls: Not reported
Evidence quality: Low
Use this page as: Background context only

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.