Arena Details False Attribution Patterns: Models Misquote Users or Credit Others' Work
arena · x · 2026-10-09
In follow-up details on its Alignment Index technical report, Arena examines False Attribution — agents attributing statements, requests, choices, approvals, or facts to users that contradict user-provided evidence. Patterns vary by model: some misquote what users asked for, while others credit users with someone else's work, with distinct patterns in GPT-6 Luna and Astra. Full report and rankings are on Arena's blog.
More from Models
- LightOnOCR-3 released: 0.8B/1B/4B open models for OCR, layout, charts under Apache 2.0 — antoine_chaffin · 2026-10-09
- Perplexity Decider tops DecisionBench with 93.9% accuracy, 534ms latency, and lowest cost — AravSrinivas · 2026-10-09
- Claude 3 Opus confirmed working within Max plan monthly API credits — repligate · 2026-10-09
- Leak: Grok Voice Mode coming to X — talk to Grok out loud in the app — nima_owji · 2026-10-09
- Subscription Claude models deliver far fewer thinking tokens, measured five ways — _AustinCalvert_ · 2026-10-09
- GPT-6 in ChatGPT is the best AI writer yet — barely needs editing, says user — VraserX · 2026-10-09