Disentangling Robustness and Sycophancy in Multilingual LLMs
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
A new paper introduces the SC-matrix, a framework that splits multilingual LLM sycophancy into four cells by crossing whether a model answers correctly without pressure with whether it abandons that answer under user pressure.
Score
0.60total under rubric v2.0
- Significance0.56
- Reader interest0.65
- Audience breadth0.54
- Practical relevance0.64
- Substantiated0.74
- Technical depth0.82
- New information0.85
- Counts against: Promotional0.03
- Counts against: Overclaim0.38
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 | 0.65 | 0.35 | 0.68 | 0.56 | 0.33 | +0.25 | +0.140 |
| Reader interest | 0.55 | 0.55 | 0.84 | 0.65 | 0.29 | +0.20 | +0.129 |
| Audience breadth | 0.62 | 0.45 | 0.55 | 0.54 | 0.17 | +0.10 | +0.054 |
| Practical relevance | 0.75 | 0.55 | 0.62 | 0.64 | 0.20 | +0.15 | +0.096 |
| Substantiated | 0.95 | 0.70 | 0.58 | 0.74 | 0.37 | +0.10 | +0.074 |
| Technical depth | 0.94 | 0.70 | 0.82 | 0.82 | 0.24 | +0.10 | +0.082 |
| New information | 0.91 | 0.70 | 0.93 | 0.85 | 0.23 | +0.10 | +0.085 |
| Promotional | 0.04 | 0.05 | 0.01 | 0.03 | 0.04 | −0.15 | −0.005 |
| Overclaim | 0.31 | 0.35 | 0.48 | 0.38 | 0.17 | −0.15 | −0.057 |
| Sum of contributions | +0.598 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.598 | ||||||
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.