WL
Weida Liang
cs.CLcs.AIcs.LG
On Valency
published · living versionsW_7ufmqht5·v1 · currentpublished
When Self-Verification Hurts: Calibrated Answer Repair for Financial Question Answering
with Celine Guo, Yujian Fu, Anqi Dang, Yanzheng Jin +2
1 version
Preprints & journals
4 papers in the corpus · 2026Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning2610.20836v1 · Weida Liang, Kenji Kawaguchi2026 · 0 citationsarXiv
Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback2610.18656v1 · Weida Liang, Kenji Kawaguchi2026 · 0 citationsarXiv
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents2610.06830v1 · Haozhen Zhang, Haodong Yue, Quanyu Long et al.2026 · 0 citationsarXiv
Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance2602.22583v2 · Weida Liang, Yiyou Sun, Shuyuan Nan et al.2026 · 0 citationsarXiv
Career total: 4 works. 4 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.