REVIEW 6 cited by
Acquiescence Bias in Large Language Models
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
Acquiescence Bias in Large Language Models
read the original abstract
Acquiescence bias, i.e. the tendency of humans to agree with statements in surveys, independent of their actual beliefs, is well researched and documented. Since Large Language Models (LLMs) have been shown to be very influenceable by relatively small changes in input and are trained on human-generated data, it is reasonable to assume that they could show a similar tendency. We present a study investigating the presence of acquiescence bias in LLMs across different models, tasks, and languages (English, German, and Polish). Our results indicate that, contrary to humans, LLMs display a bias towards answering no, regardless of whether it indicates agreement or disagreement.
Forward citations
Cited by 6 Pith papers
-
Tag Questions and the Generational Reversal of Sycophancy Across 45 Language Models
Across 45 LLMs, the 'right?' tag effect flips from sycophantic to resistant over four years of releases, while the 'maybe?' tag raises agreement in every model — anti-sycophancy training is grammar-keyed and one-sided.
-
Benchmarking LLM Competence on Logical Inference over Probability Operators
Only 9 of 29 tested LLMs beat a chance-level competence floor on valid/invalid inferences over probability operators like "probably" and "might"; most answer from a fixed yes/no bias.
-
Benchmarking LLM Competence on Logical Inference over Probability Operators
Only 9 of 29 LLMs exceed chance on inferences over probability operators, and most models answer from a stable Yes/No bias rather than tracking the logic.
-
Benchmarking LLM Competence on Logical Inference over Probability Operators
Most of 29 LLMs answer probability-operator inference questions from a fixed Yes/No bias, with only 9 clearing a 50% competence floor.
-
AMEL: Accumulated Message Effects on LLM Judgments
LLMs exhibit an accumulated message effect where conversation history saturated with positive or negative evaluations biases subsequent judgments, with larger shifts on uncertain items, a negativity asymmetry, and no ...
-
AMEL: Accumulated Message Effects on LLM Judgments
LLMs exhibit an accumulated message effect where conversation history polarity biases subsequent judgments, stronger for high-entropy items, independent of context length, and with a negativity bias.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.