Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Reset Is Not Recovery: Evaluating Recoverability from False Conversational Context via Sycophancy Hysteresis
Adi Shnaidman
Grounded language models are usually evaluated by adding relevant context, but multiturn dialogue also contains unsupported user claims that may contaminate later factual answers.…
cs.CL2025
Activation Steering for Masked Diffusion Language Models
Adi Shnaidman, Erin Feiglin, Osher Yaari +3
Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs f…