LLMs replacing human participants harmfully misportray, flatten identity groups (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: LLMs replacing human participants harmfully misportray, flatten identity groups

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: LLMs are more persuasive than incentivized human persuaders

LLMs are more persuasive than incentivized human persuaders (arxiv.org)

109 points by flornt 1 year ago | 87 comments

Screenshot of arxiv.org: LLMs should not replace therapists

LLMs should not replace therapists (arxiv.org)

210 points by layer8 1 year ago | 276 comments

Screenshot of arxiv.org: Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking

Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking (arxiv.org)

42 points by favoboa 1 year ago | 37 comments

Screenshot of arxiv.org: LLMorphism: When humans come to see themselves as language models

LLMorphism: When humans come to see themselves as language models (arxiv.org)

60 points by okey 5 months ago | 39 comments

Screenshot of arxiv.org: Understanding Transformers via N-gram Statistics

Understanding Transformers via N-gram Statistics (arxiv.org)

110 points by pona-a 1 year ago | 13 comments

Screenshot of arxiv.org: Large language models often know when they are being evaluated

Large language models often know when they are being evaluated (arxiv.org)

60 points by jonbaer 1 year ago | 74 comments