Pith. sign in

REVIEW 3 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

arxiv 2405.20253 v1 pith:RWWGOCWX submitted 2024-05-30 cs.CL

classification cs.CL
keywords modelspersonasgenerationlesspersonatextassociatedbiases
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Localizing Persona Representations in LLMs

    cs.CL 2025-05 conditional novelty 6.0 of 10

    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.

  2. Stylometry recognizes human and LLM-generated texts in short samples

    cs.CL 2025-07 conditional novelty 5.0 of 10

    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 ...

  3. DinoCompanion: An Attachment-Theory Informed Multimodal Robot for Emotionally Responsive Child-AI Interaction

    cs.AI 2025-06 reject novelty 5.0 of 10

    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...

Pith tools