Who Is Sycophantic to Whom? Confident LLMs, Human Deference, and the Collapse of Trust Calibration

No. 75 of 245 · arXiv · Deepthika S, Pawni Yadav, B. Sankar · published 23 Oct 2026, 04:00 UTC · 80 min read

AI & machine learning
Paper

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

A new arXiv paper by Deepthika S and B. Sankar tests whether users defer to confident, consistent LLMs even when those models are wrong. In a within-subjects study of 32 participants learning science topics from assistants with 0 to 100 percent planted falsehoods, quiz scores fell from 7.4 to 2.9…

Read the original at arxiv.org. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.67total under rubric v2.0Contestedjudges differ by 0.63 on technical depth

Significance0.64
Reader interest0.73
Audience breadth0.68
Practical relevance0.72
Substantiated0.83
Technical depth0.74
New information0.86
Counts against: Promotional0.04
Counts against: Overclaim0.34

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.70	0.45	0.78	0.64	0.33	+0.25	+0.161
Reader interest	0.66	0.60	0.93	0.73	0.33	+0.20	+0.146
Audience breadth	0.77	0.55	0.72	0.68	0.22	+0.10	+0.068
Practical relevance	0.79	0.60	0.78	0.72	0.19	+0.15	+0.109
Substantiated	0.96	0.70	0.84	0.83	0.26	+0.10	+0.083
Technical depth	0.97	0.35	0.89	0.74	0.63 , above the contested threshold	+0.10	+0.074
New information	0.90	0.70	0.98	0.86	0.28	+0.10	+0.086
Promotional	0.06	0.05	0.01	0.04	0.05	−0.15	−0.006
Overclaim	0.41	0.30	0.32	0.34	0.11	−0.15	−0.051
Sum of contributions							+0.669
Claim-check penalty							0.000
Total, as published							0.669

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN —

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.