PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning

Hyeong Kyu Choi, Yixuan Li
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8722-8739, 2024.

Abstract

Large Language Models (LLMs) are trained on massive text corpora, which are encoded with diverse personality traits. This triggers an interesting goal of eliciting a desired personality trait from the LLM, and probing its behavioral preferences. Accordingly, we formalize the persona elicitation task, aiming to customize LLM behaviors to align with a target persona. We present Persona In-Context Learning (PICLe), a novel persona elicitation framework grounded in Bayesian inference. At the core, PICLe introduces a new ICL example selection criterion based on likelihood ratio, which is designed to optimally guide the model in eliciting a specific target persona. We demonstrate the effectiveness of PICLe through extensive comparisons against baseline methods across three contemporary LLMs. Code is available at https://github.com/deeplearning-wisc/picle.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-choi24e, title = {{PICL}e: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning}, author = {Choi, Hyeong Kyu and Li, Yixuan}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {8722--8739}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/choi24e/choi24e.pdf}, url = {https://proceedings.mlr.press/v235/choi24e.html}, abstract = {Large Language Models (LLMs) are trained on massive text corpora, which are encoded with diverse personality traits. This triggers an interesting goal of eliciting a desired personality trait from the LLM, and probing its behavioral preferences. Accordingly, we formalize the persona elicitation task, aiming to customize LLM behaviors to align with a target persona. We present Persona In-Context Learning (PICLe), a novel persona elicitation framework grounded in Bayesian inference. At the core, PICLe introduces a new ICL example selection criterion based on likelihood ratio, which is designed to optimally guide the model in eliciting a specific target persona. We demonstrate the effectiveness of PICLe through extensive comparisons against baseline methods across three contemporary LLMs. Code is available at https://github.com/deeplearning-wisc/picle.} }
Endnote
%0 Conference Paper %T PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning %A Hyeong Kyu Choi %A Yixuan Li %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-choi24e %I PMLR %P 8722--8739 %U https://proceedings.mlr.press/v235/choi24e.html %V 235 %X Large Language Models (LLMs) are trained on massive text corpora, which are encoded with diverse personality traits. This triggers an interesting goal of eliciting a desired personality trait from the LLM, and probing its behavioral preferences. Accordingly, we formalize the persona elicitation task, aiming to customize LLM behaviors to align with a target persona. We present Persona In-Context Learning (PICLe), a novel persona elicitation framework grounded in Bayesian inference. At the core, PICLe introduces a new ICL example selection criterion based on likelihood ratio, which is designed to optimally guide the model in eliciting a specific target persona. We demonstrate the effectiveness of PICLe through extensive comparisons against baseline methods across three contemporary LLMs. Code is available at https://github.com/deeplearning-wisc/picle.
APA
Choi, H.K. & Li, Y.. (2024). PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:8722-8739 Available from https://proceedings.mlr.press/v235/choi24e.html.

Related Material