Excited to share our new paper, “What AI Benchmarks Actually Measure: Adapting Convergent and Discriminant Validity to Interrogate Fifty-Six AI Benchmarks,” accepted as an oral at COLM! arxiv.org/pdf/2609.08812
Meera Desai
Researcher with public evidence across Models & releases, AI research, Evaluation & benchmarks.
- AI signals
- 3 past 30d
- Sources
- 2 distinct domains
- Discussões
- 0 past 30d
- Latest signal
- 22d ago
Articles & links
Come find us at COLM, I’ll be presenting this paper next Thursday afternoon (10/8, oral session 6 and poster session 6). Full paper here: arxiv.org/abs/2609.08812
- A COLM 2026 paper runs 53 models through 56 capability and safety benchmarks and finds many benchmark labels do not match what the tests measure.
- BBQ-accuracy, assigned to the bias category, correlates more strongly with reasoning benchmarks than with other bias benchmarks in its own group.
- On safety concepts, correlations between model rankings on benchmarks sharing the same assigned concept are often weak, the authors report.
To make our analysis possible, we collected model outputs and scores from 53 models on 56 capability and safety benchmarks. This data, including item-level model responses and score, is available here huggingface.co/datasets/mad...
In Meera Desai's orbit
Center = Meera Desai. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.
Are you Meera Desai? Show it.
Add the Who’s Who of AI badge to your site or bio. It links back to this profile.
Markdown: [](https://aiweekly.co/whos-who/person/madesai-bsky-social)