Knowledge Graph Question Answering (KGQA) requires multi-step reasoning over a large, structured search space, where free-form LLM planning can hallucinate intermediate subgraphs or query sketches and yield unexecutable reasoning. We propose READS, a constraint-guided discriminative reasoning framework that makes KGQA...
Mu-Fan Xu, Ke-Hai Chen, Xue-Feng Bai et al.· IEEE Transactions on Knowled...· 0 citations
Maximum Likelihood Reinforcement Learning (MaxRL) targets prompt-wise log-success and has shown strong performance on reasoning tasks. Under finite rollout budgets, however, the estimator used by MaxRL attenuates each prompt's likelihood gradient by a factor that depends on its success probability and rollout count. Un...
Zi-Hao Chen, Fan-Xiang Xiong, Hong-Ran Ren et al.· 0 citations
Understanding where and why Graphical User Interface (GUI) agents fail is essential for building more reliable systems, yet current evaluation relies on step accuracy, a metric that treats each screen independently and overlooks the underlying structure of GUI environments. This leads to two critical blind spots: (1) f...
Shao-Qing Zhang, Ke-Hai Chen, Xue-Feng Bai et al.· 0 citations
Test-time reinforcement learning (TTRL) improves the reasoning capabilities of large language models without labeled data by updating the policy with pseudo-labels constructed through majority voting. While effective, the reward signal assigned from majority voting is highly sensitive to consensus strength, defined as...
Kunbin Xu, Xingzuo Li, Xue-Feng Bai et al.· 1 citation
DualAnchor is proposed, a gloss-free LLM-based SLT training framework that couples two complementary anchors for linguistically fluent and visually faithful generation that achieves strong overall performance on both PHOENIX-2014T and CSL-Daily.
Hongbin Zhang, Jun-Hao Liu, Xue-Feng Bai et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
