ECCV 2026 talk proposes desiderata for how LLMs should communicate uncertainty
abursuc · x · 2026-09-08
At an ECCV 2026 workshop (#uncv2026), Christian Hardmeier presented 'Towards Anthropomimetic Uncertainty: Desiderata for Uncertainty Communication in Large Language Models,' arguing that systems must express uncertainty in ways users can correctly interpret — uncertainty communication as an epistemic marker, not just internal quantification. A notable topic at the intersection of HCI and model trustworthiness.
Related event: ECCV 2026 workshop covers LLM uncertainty and multimodal diagnosis(3 posts)→
More from Research
- Mathematician argues papers should shift from proving conjectures to sharing insight — tak3sh8 · 2026-09-08
- Niantic's AutoCompass trains accurate visual localization from noisy GPS labels — ducha_aiki · 2026-09-08
- Apex unveils Astra, an automated AI research system aimed at AI improving AI — thetripathi58 · 2026-09-08
- More Ukrainian teams join CV research map with USDZ-prediction approach to object alignment and animation — ducha_aiki · 2026-09-08
- JustRL II adds token-level critic to GRPO for 128k long-CoT RL, lifting 2B model AIME25 from 61 to 81 — zibuyu9 · 2026-09-08
- Helsinki's Luigi Acerbi recruiting PhD/postdoc on amortized probabilistic ML for decision-making — LucaAmb · 2026-09-08