Tag
This chapter reviews recent advances in weakly supervised learning, introducing confidence-difference classification, relaxed assumptions for complementary-label learning, and an evaluation framework for partial-label learning.
This paper proposes a two-stage approach for early failure alerting in dialogs and LLM-agent trajectories, addressing the challenge of sparse evidence by learning turn-level failure evidence from trajectory labels and using an attention-based predictor with a preference-conditioned stopping policy (α-STOP) to achieve controllable accuracy-earliness trade-offs.