Pith. sign in

REVIEW 4 cited by

Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.02584 v1 pith:4BWUAGOT submitted 2024-10-03 cs.CL cs.CY

Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions

classification cs.CL cs.CY
keywords biasesimplicitllmsmitigateinteractionsmulti-agentbiasfine-tuning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to human-generated data. Given that LLMs are being used to gain insights into various societal aspects, it is essential to mitigate these biases. To that end, our study investigates the presence of implicit gender biases in multi-agent LLM interactions and proposes two strategies to mitigate these biases. We begin by creating a dataset of scenarios where implicit gender biases might arise, and subsequently develop a metric to assess the presence of biases. Our empirical analysis reveals that LLMs generate outputs characterized by strong implicit bias associations (>= 50\% of the time). Furthermore, these biases tend to escalate following multi-agent interactions. To mitigate them, we propose two strategies: self-reflection with in-context examples (ICE); and supervised fine-tuning. Our research demonstrates that both methods effectively mitigate implicit biases, with the ensemble of fine-tuning and self-reflection proving to be the most successful.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Contagion Networks: Evaluator Preference Propagation in Multi-Agent LLM Systems

    cs.LG 2026-06 unverdicted novelty 7.0

    Contagion Networks framework measures evaluator bias propagation in 3-agent LLM systems using the same base model, reporting gamma values of 0.157-0.352 and a 72.4% reduction in contagion when increasing evaluator com...

  2. Contagion Networks: Evaluator Preference Propagation in Multi-Agent LLM Systems

    cs.LG 2026-06 unverdicted novelty 6.0

    Introduces Contagion Networks framework and measures preference propagation in 3-agent LLM setups, finding architectural priors dominate prompts, topology affects spread, and larger committees reduce contagion by ~69%.

  3. Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems

    cs.MA 2026-04 unverdicted novelty 6.0

    Multi-agent systems amplify minor stochastic biases into systemic polarization via echo-chamber effects in structured workflows, even with neutral agents.

  4. Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review

    cs.SE 2026-04 unverdicted novelty 2.0

    A rapid review of fairness in LLM-enabled multi-agent systems for the software development lifecycle concludes that the field lacks standardized evaluations, broad coverage, and effective governance, leaving it unprep...