REVIEW 4 cited by
Evaluating Large Language Model Biases in Persona-Steered Generation
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
read the original abstract
The task of persona-steered text generation requires large language models (LLMs) to generate text that reflects the distribution of views that an individual fitting a persona could have. People have multifaceted personas, but prior work on bias in LLM-generated opinions has only explored multiple-choice settings or one-dimensional personas. We define an incongruous persona as a persona with multiple traits where one trait makes its other traits less likely in human survey data, e.g. political liberals who support increased military spending. We find that LLMs are 9.7% less steerable towards incongruous personas than congruous ones, sometimes generating the stereotypical stance associated with its demographic rather than the target stance. Models that we evaluate that are fine-tuned with Reinforcement Learning from Human Feedback (RLHF) are more steerable, especially towards stances associated with political liberals and women, but present significantly less diverse views of personas. We also find variance in LLM steerability that cannot be predicted from multiple-choice opinion evaluation. Our results show the importance of evaluating models in open-ended text generation, as it can surface new LLM opinion biases. Moreover, such a setup can shed light on our ability to steer models toward a richer and more diverse range of viewpoints.
Forward citations
Cited by 4 Pith papers
-
Localizing Persona Representations in LLMs
Persona information is most separable in the final third of LLM layers, and in Llama3's last layer ethical personas share 17.6% of salient activations while political personas have 2.1% to 5.5% unique activations.
-
Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection
On StereoSet and SBIC, a trained DeBERTa encoder that selects per-input prompt compositions from 64 options raises macro F1 above every fixed composition, but on CobraFrames it falls below the best fixed composition.
-
Stylometry recognizes human and LLM-generated texts in short samples
Stylometric features and tree-based classifiers separate human-written Wikipedia summaries from LLM-generated texts with high cross-validated accuracy on a new seven-class benchmark, though performance drops on other ...
-
DinoCompanion: An Attachment-Theory Informed Multimodal Robot for Emotionally Responsive Child-AI Interaction
A child-facing robot trained with an attachment-theory-informed preference optimization is claimed to beat GPT-4o and Gemini-2.5-Pro on a new ten-competency benchmark, though evaluation and derivation issues undermine...
Discussion (0). Continue with ORCID to comment.