Chain-of-Thought reasoning can sound plausible while being unfaithful. Is there a way to test that directly by looking inside the model? Our new work led by @qiaw99.bsky.social w/ @apepa.bsky.social et al. 📜 Pre-print: arxiv.org/abs/2609.23065
Nils Feldhus
Directory member with public evidence across Models & releases, AI business, AI research.
- AI signals
- 1 past 30d
- Sources
- 1 distinct domains
- Discussions
- 0 past 30d
- Latest signal
- 11d ago
Articles & links
📢 Call for Papers: YNLG 2026 The Young Researchers in Natural Language Generation workshop is a 2d in-person event part of INLG 2026 @inlg.bsky.social in Utrecht 🇳🇱, with poster sessions, keynote talks, roundtable discussions, and a one-day hackathon. Due: August 10, 2026 ynlg…
Recent commentary
🙋 Looking for emergency reviewers for ARR May / #EMNLP2026 Topics: Interpretability/Explainability, RAG, Answer Attribution, Knowledge Conflicts If you're willing to complete a review before July 6 AoE, please reply or send a DM!
In Nils Feldhus's orbit
Center = Nils Feldhus. 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 Nils Feldhus? 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/nfel-bsky-social)