2 citations · 6 across the 17 of their papers we have counts for
4 papers · 1 filter
HindSearch: Trajectory-Level Hindsight Critique for Search-Augmented Reinforcement Learning
Haowei Liu, Jiamian Wang, Hsin-Tai Wu +2
Search-augmented LM agents are typically trained with a binary exact-match reward, which throws away most of what a failed trajectory tells us about why it failed. We introduce Hin…
ReliableTableQA:How Much Supervision Does Reliability Annotation Need?
Huei-Chung Hu, Hsin-Tai Wu, Koyo Kobayashi
We introduce ReliableTableQA, a framework for training an LLM to annotate the statistical reliability of tabular QA results, not whether the query is answerable, but whether the co…
Leveraging an Efficient and Semantic Location Embedding to Seek New Ports of Bike Share Services
Yuan Wang, Chenwei Wang, Yinan Ling +3
For short distance traveling in crowded urban areas, bike share services are becoming popular owing to the flexibility and convenience. To expand the service coverage, one of the k…
PPD: Permutation Phase Defense Against Adversarial Examples in Deep Learning
Mehdi Jafarnia-Jahromi, Tasmin Chowdhury, Hsin-Tai Wu +1
Deep neural networks have demonstrated cutting edge performance on various tasks including classification. However, it is well known that adversarially designed imperceptible pertu…