REVIEW 5 cited by
A Multi-LLM Debiasing Framework
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
Signed reviews
read the original abstract
Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities. Despite significant advancements in bias mitigation techniques using data augmentation, zero-shot prompting, and model fine-tuning, biases continuously persist, including subtle biases that may elude human detection. Recent research has shown a growing interest in multi-LLM approaches, which have been demonstrated to be effective in improving the quality of reasoning and factuality in LLMs. Building on this approach, we propose a novel multi-LLM debiasing framework aimed at reducing bias in LLMs. Our work is the first to introduce and evaluate two distinct approaches within this framework for debiasing LLMs: a centralized method, where the conversation is facilitated by a single central LLM, and a decentralized method, where all models communicate directly. Our findings reveal that our multi-LLM framework significantly reduces bias in LLMs, outperforming the baseline method across several social groups.
Forward citations
Cited by 5 Pith papers
-
From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text
Vision-language models produce more positive chart summaries for high-income countries than for middle- or low-income countries, and a simple positive prompt only partly fixes the bias.
-
Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards
Assigning personas to Chinese LLMs amplifies toxic output relative to default behavior, while refusal rates shift systematically with persona gender and target social group.
-
Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration
A survey of multi-LLM systems in edge computing, covering architectures, enabling technologies, trust mechanisms, applications, and open datasets for edge general intelligence.
-
A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network
A weighted Byzantine fault tolerance consensus for multi-LLM networks is proposed, but its security proof assumes equal weights while the protocol lets the leader set weights, and its quality evaluation is self-referential.
-
A Trustworthy Multi-LLM Network: Challenges,Solutions, and A Use Case
A blockchain-consensus layer over multiple LLMs is proposed to select power-allocation strategies, with a false-base-station defense simulation that claims near-optimal performance.
Discussion (0). Continue with ORCID to comment.