Xiaotong Ji
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
AI×1NLP×1Logic×1Crypto×1Comp. Eng.×1
Frequent co-authors
Research Timeline
2026
Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout
The paper proposes FinSec, a novel four-tier security detection framework, to robustly identify complex financial risks and suspicious dialogue patterns in LLM-powered financial agents, achieving state-of-the-art performance.
Risk-Controlled Lean-as-Judge for Natural-Language Mathematical Reasoning
The paper introduces COVCAL, a risk-controlled method that precisely determines when a partial formalization signal from an autoformalizer can be trusted to certify the correctness of natural-language mathematical answers.
Highlighted terms show continued research focus across papers
Papers
cs.AIcs.CLcs.LORecentMay 27, 2026
Risk-Controlled Lean-as-Judge for Natural-Language Mathematical Reasoning
The paper introduces COVCAL, a risk-controlled method that precisely determines when a partial formalization signal from an autoformalizer can be trusted to certify the correctness of natural-language…
View →
cs.CRcs.CERecentApr 10, 2026