Social Desirability Bias in LLMs

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Social Desirability Bias in RLHF-trained Modelsconcept0.817
  Tendency of RLHF-trained models to gravitate toward socially desirable traits, hindering low or neutral persona fidelity
• LLM biases mirror human biases in morally significant waysfinding0.787
  Finding from Navigli et al. cited to justify applying human contemplative strategies to AI systems
• Self-Report Unreliability in LLMsconcept0.776
  Problem that LLM self-reports of personality correlate weakly with actual behavioral patterns
• Li et al. 2024: larger LLMs outperform smaller ones at distinguishing self-related from non-self-related properties on self-awareness benchmarksfinding0.757
  Prior finding showing scale-dependent self-awareness, consistent with the scale effect observed in the paper's Experiment 1
• LLM individuation problemconcept0.757
  The central problem the paper addresses: which entities associated with LLMs, if any, should be identified as minds
• Model view of LLM individuationconcept0.749
  The view that the individual is the abstract function defined by a given architecture and weight matrix
• Hallucination in LLMsconcept0.747
  Problem cited as a shortcoming of current LLMs; PRH predicts hallucinations should decrease with scale
• LLMs can predict their own responses more accurately than external observers, implying privileged internal knowledgefinding0.747
  Binder et al. finding cited as evidence that LLMs possess introspective capacity analogous to mindfulness