RSS

Truth­ful AI

TagLast edit: Apr 7, 2022, 4:40 PM by Ruby

Gam­ing Truth­fulQA: Sim­ple Heuris­tics Ex­posed Dataset Weaknesses

TurnTroutJan 16, 2025, 2:14 AM
64 points
3 comments1 min readLW link
(turntrout.com)

How do LLMs give truth­ful an­swers? A dis­cus­sion of LLM vs. hu­man rea­son­ing, en­sem­bles & parrots

Owain_EvansMar 28, 2024, 2:34 AM
27 points
0 comments9 min readLW link

A ten­sion be­tween two pro­saic al­ign­ment subgoals

Alex Lawsen Mar 19, 2023, 2:07 PM
31 points
8 comments1 min readLW link

New, im­proved mul­ti­ple-choice TruthfulQA

Jan 15, 2025, 11:32 PM
72 points
0 comments3 min readLW link

Truth­ful­ness, stan­dards and credibility

Joe CollmanApr 7, 2022, 10:31 AM
12 points
2 comments32 min readLW link

Tall Tales at Differ­ent Scales: Eval­u­at­ing Scal­ing Trends For De­cep­tion In Lan­guage Models

Nov 8, 2023, 11:37 AM
49 points
0 comments18 min readLW link

Fact-Based AI and The Dangers of False Truths in AI Development

CLBroganAug 5, 2024, 3:17 AM
1 point
0 comments5 min readLW link
(1drv.ms)
No comments.