1 citations · 1 across the 5 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.CL2026
You Are What You Read: Misalignment via In-Context Persona Induction
Kyuhee Kim, Benjamin Berczi, Cozmin Ududec
Broad misalignment has been produced by finetuning on narrow data, harmful or benign, and in context only by demonstrations of the undesirable behaviour itself. We show that benign…
cs.CR2026
ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration
Chengheng Li-Chen, Kyuhee Kim
Regulatory regimes such as the EU AI Act mandate machine-readable marking of synthetic text, but existing watermark detectors rely on the generating LM and on heuristic thresholds…
cs.AI2026
Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning
Kyuhee Kim, Auguste Poiroux, Antoine Bosselut
Formal verification guarantees proof validity but not formalization faithfulness. For natural-language logical reasoning, where models construct axiom systems from scratch without…