Dynamically adjusting beta via LLM-as-judge downweights biased comparisons to learn more rational reward models from flawed human preferences.
2403.00811 , primaryclass =
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Numeric anchors embedded in images systematically bias VLM quality judgments more than severe visual degradation, with layer-wise probing showing that anchor-saturated layers are suboptimal for quality prediction.
LLMs exhibit persistent inertia in value orientations, with harm avoidance and fairness remaining skewed across persona prompts.
A literature review that categorizes bias in LLMs, surveys evaluation and mitigation techniques, and discusses ethical implications.
citing papers explorer
-
Mitigating Cognitive Bias in RLHF by Altering Rationality
Dynamically adjusting beta via LLM-as-judge downweights biased comparisons to learn more rational reward models from flawed human preferences.
-
Don't Look at the Numbers: Visual Anchoring Bias and Layer-wise Representation in VLMs
Numeric anchors embedded in images systematically bias VLM quality judgments more than severe visual degradation, with layer-wise probing showing that anchor-saturated layers are suboptimal for quality prediction.
-
Inertia in Moral and Value Judgments of Large Language Models
LLMs exhibit persistent inertia in value orientations, with harm avoidance and fairness remaining skewed across persona prompts.
-
Bias in Large Language Models: Origin, Evaluation, and Mitigation
A literature review that categorizes bias in LLMs, surveys evaluation and mitigation techniques, and discusses ethical implications.
- AMEL: Accumulated Message Effects on LLM Judgments