paper-with-me

홈 › Papers

Learning to Partially Defer for Sequences

2025-02-03 · Sahana Rayan, Ambuj Tewari

In the Learning to Defer (L2D) framework, a prediction model can either make a prediction or defer it to an expert, as determined by a rejector. Current L2D methods train the rejector to decide whether to reject the entire prediction, which is not desirable when the model predicts long sequences. We present an L2D setting for sequence outputs where the system can defer specific outputs of the whole model prediction to an expert in an effort to interleave the expert and machine throughout the prediction. We propose two types of model-based post-hoc rejectors for pre-trained predictors: a token-level rejector, which defers specific token predictions to experts with next token prediction capabilities, and a one-time rejector for experts without such abilities, which defers the remaining sequence from a specific point onward. In the experiments, we also empirically demonstrate that such granular deferrals achieve better cost-accuracy tradeoffs than whole deferrals on Traveling salesman solvers and News summarization models.

📄 PDF Abstract BibTeX arXiv:2502.01459

Code (0)

등록된 구현이 없습니다.

Tasks

News SummarizationPrediction

Similar Papers 제목 키워드 기반

Learning-to-defer for sequential medical decision-making under uncertainty

2021-09-13 · Shalmali Joshi, Sonali Parbhoo, Finale Doshi-Velez

Learning-to-defer is a framework to automatically defer decision-making to a human expert when ML-based decisions are deemed unreliable. Existing learning-to-defer frameworks are not designed for sequential settings. Tha…

Decision MakingDecision Making Under UncertaintyModel-based Reinforcement LearningReinforcement Learning (RL)+1

The Partially Observable Off-Switch Game

2024-11-25 · Andrew Garber, Rohan Subramani, Linus Luu, Mark Bedaywi 외

A wide variety of goals could cause an AI to disable its off switch because "you can't fetch the coffee if you're dead" (Russell 2019). Prior theoretical work on this shutdown problem assumes that humans know everything …

From Soft Classifiers to Hard Decisions: How fair can we be?

2018-10-03 · Ran Canetti, Aloni Cohen, Nishanth Dikkala, Govind Ramnarayan 외

A popular methodology for building binary decision-making classifiers in the presence of imperfect information is to first construct a non-binary "scoring" classifier that is calibrated over all protected groups, and the…

Decision MakingFairness

A Causal Framework for Evaluating Deferring Systems

2024-05-29 · Filippo Palomba, Andrea Pugnana, José Manuel Alvarez, Salvatore Ruggieri

Deferring systems extend supervised Machine Learning (ML) models with the possibility to defer predictions to human experts. However, evaluating the impact of a deferring strategy on system accuracy is still an overlooke…

Causal Inference

Characterizing and Predicting Email Deferral Behavior

2019-01-14 · Sarrafzadeh Bahareh, Awadallah Ahmed Hassan, Lin Christopher H., Lee Chia-Jung 외

Email triage involves going through unhandled emails and deciding what to do with them. This familiar process can become increasingly challenging as the number of unhandled email grows. During a triage session, users com…