Conversational Query Rewriting (CQR) turns a context dependent user turn into a standalone query for a retriever, and most methods do this in a single step from the dialogue history before retrieving once. The rewrite is therefore fixed before any corpus evidence is available to correct its reference resolution or its...
João Coelho, Hong Wang, Jie Yuan et al.· 0 citations
This work proposes a new paradigm: Test-Time Policy Adaptation for Multi-Turn Interactions (T2PAM), which utilizes user feedback from the ongoing interaction as a reward signal to estimate a latent optimal policy aligned with user preferences, then updates a small subset of parameters to steer the model toward this pol...
Chen-Xing Wei, Hong Wang, Ying He et al.· arXiv.org· 4 citations
This work introduces RECAP (REdundancy-aware Credit Assignment via Propagation), which addresses this limitation by assigning credit where it is due based on both a step's downstream role in the reasoning structure and its contribution to solving the problem correctly.
Yu-Qing Zhou, Hong Wang, Man-Qing Mao et al.· 0 citations
RIPPLE (Replay-Informed Persistent Policy Localization and Editing), which separates where an edit is made from whether it remains safe to persist after composition, and improves validation success by up to 23.1% and yields positive gains on two additional frozen language-model backbones, while maintaining edit efficie...
Man-Qing Mao, Hong Wang, Samson Koelle et al.· 0 citations
We introduce Xiaomi-TabLDM, a tabular large data foundation model for classification and regression via in-context learning, which delivers superior prediction accuracy without requiring task-specific fine-tuning. Pretrained exclusively on synthetic data generated from structural causal models (SCMs), our model enables...
Xiaomi-TabLDM Team Penghui Wang, Wei Liu, Hong Wang et al.· 0 citations
Recoverability-Aware Intervention Learning (RAIL), a training-time framework that learns how to generate rollouts based on the improvement produced by each intervention, consistently improves performance under limited rollout budgets.
Zheyuan Zhang, Man-Qing Mao, Hong Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
