Implicit Personalization in Language Models: A Systematic Study
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917824307396608 |
|---|---|
| author | Jin, Zhijing Heil, Nils Liu, Jiarui Dhuliawala, Shehzaad Qi, Yahang Schölkopf, Bernhard Mihalcea, Rada Sachan, Mrinmaya |
| author_facet | Jin, Zhijing Heil, Nils Liu, Jiarui Dhuliawala, Shehzaad Qi, Yahang Schölkopf, Bernhard Mihalcea, Rada Sachan, Mrinmaya |
| contents | Implicit Personalization (IP) is a phenomenon of language models inferring a user's background from the implicit cues in the input prompts and tailoring the response based on this inference. While previous work has touched upon various instances of this problem, there lacks a unified framework to study this behavior. This work systematically studies IP through a rigorous mathematical formulation, a multi-perspective moral reasoning framework, and a set of case studies. Our theoretical foundation for IP relies on a structural causal model and introduces a novel method, indirect intervention, to estimate the causal effect of a mediator variable that cannot be directly intervened upon. Beyond the technical approach, we also introduce a set of moral reasoning principles based on three schools of moral philosophy to study when IP may or may not be ethically appropriate. Equipped with both mathematical and ethical insights, we present three diverse case studies illustrating the varied nature of the IP problem and offer recommendations for future research. Our code is at https://github.com/jiarui-liu/IP, and our data is at https://huggingface.co/datasets/Jerry999/ImplicitPersonalizationData. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14808 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Implicit Personalization in Language Models: A Systematic Study Jin, Zhijing Heil, Nils Liu, Jiarui Dhuliawala, Shehzaad Qi, Yahang Schölkopf, Bernhard Mihalcea, Rada Sachan, Mrinmaya Computation and Language Artificial Intelligence Computers and Society Human-Computer Interaction Machine Learning Implicit Personalization (IP) is a phenomenon of language models inferring a user's background from the implicit cues in the input prompts and tailoring the response based on this inference. While previous work has touched upon various instances of this problem, there lacks a unified framework to study this behavior. This work systematically studies IP through a rigorous mathematical formulation, a multi-perspective moral reasoning framework, and a set of case studies. Our theoretical foundation for IP relies on a structural causal model and introduces a novel method, indirect intervention, to estimate the causal effect of a mediator variable that cannot be directly intervened upon. Beyond the technical approach, we also introduce a set of moral reasoning principles based on three schools of moral philosophy to study when IP may or may not be ethically appropriate. Equipped with both mathematical and ethical insights, we present three diverse case studies illustrating the varied nature of the IP problem and offer recommendations for future research. Our code is at https://github.com/jiarui-liu/IP, and our data is at https://huggingface.co/datasets/Jerry999/ImplicitPersonalizationData. |
| title | Implicit Personalization in Language Models: A Systematic Study |
| topic | Computation and Language Artificial Intelligence Computers and Society Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2405.14808 |