1 citations · 1 across the 6 of their papers we have counts for
4 papers · 1 filter
Human-LLM Deliberation as Interactive Proof: Conditions for Verifiability Without Transparency
Baotong Zhang, Dean Foster, João Sedoc
When an LLM supplies an argument a user could not produce, how can the user decide whether to accept its claim? Inspired by interactive proofs, we pair a computationally unbounded…
Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Ground Truth Is Unavailable
Shai Vardi, João Sedoc
Large language models are increasingly used to support organizational decisions, yet users often lack a principled basis for assessing whether to rely on a specific recommendation.…
Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction
João Sedoc, Baotong Zhang, Dean Foster
Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference-time protocol grounded in i…
Conceptors for Semantic Steering
Ilias Triantafyllopoulos, Young-Min Cho, Ren Tao +6
Activation-based steering provides control of LLM behavior at inference time, but the dominant paradigm reduces each concept to a single direction whose geometry is left largely un…