FastODT: A tree-based framework for efficient continual learning
arXiv:2603.13276v1 Announce Type: new Abstract: Machine learning models deployed in real-world settings must operate under evolving data distributions and constrained computational resources. This challenge is particularly acute in non-stationary domains such as energy time series, weather monitoring, and environmental sensing....
When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO
arXiv:2603.13134v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has emerged as an effective method for training reasoning models. While it computes advantages based on group mean, GRPO treats each output as an independent sample during the optimization and...
Cross-Domain Uncertainty Quantification for Selective Prediction: A Comprehensive Bound Ablation with Transfer-Informed Betting
arXiv:2603.08907v1 Announce Type: new Abstract: We present a comprehensive ablation of nine finite-sample bound families for selective prediction with risk control, combining concentration inequalities (Hoeffding, Empirical Bernstein, Clopper-Pearson, Wasserstein DRO, CVaR) with multiple-testing corrections (union bound, Learn Then Test fixed-sequence)...
Elenchus: Generating Knowledge Bases from Prover-Skeptic Dialogues
arXiv:2603.06974v1 Announce Type: new Abstract: We present Elenchus, a dialogue system for knowledge base construction grounded in inferentialist semantics, where knowledge engineering is re-conceived as explicitation rather than extraction from expert testimony or textual content. A human expert develops a...
Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information
arXiv:2603.07111v1 Announce Type: new Abstract: The Werewolf Game is a communication game where players' reasoning and discussion skills are essential. In this study, we present a Werewolf AI agent developed for the AIWolfDial 2024 shared task, co-hosted with the 17th...
A Comparative Study of Undue Influence and Unfair Conduct in Contract Law Using NLP and Knowledge Graphs: Bridging Common Law and Chinese Legal Systems Through Computational Legal Intelligence
This study explores intelligent identification methods for undue influence and grossly unfair clauses from the cross-perspectives of artificial intelligence and comparative contract law, focusing on the integration of intelligent text analysis and legal knowledge graph technology. By constructing a dual...
Pessimistic Auxiliary Policy for Offline Reinforcement Learning
arXiv:2602.23974v1 Announce Type: new Abstract: Offline reinforcement learning aims to learn an agent from pre-collected datasets, avoiding unsafe and inefficient real-time interaction. However, inevitable access to out-ofdistribution actions during the learning process introduces approximation errors, causing the error accumulation and...