Searcharxiv⌕ Search

arXiv subjects

Win-Bin Huang

Publications and source records attributed to Win-Bin Huang.

2 recordsLinked to original sources

TRACER: Trajectory-Aligned Learning for Multi-Turn User Simulation

Faithful user simulation is fundamental to building, evaluating, and improving interactive AI at scale. Yet current simulators often produce plausible individual responses without reproducing the intent evolution and outcomes observed in real interactions. We propose TRACER, a multi-turn user simulator that models evolving user intent and aligns simulated trajectories with real ones. TRACER is trained in two stages: supervised fine-tuning on real user dialogues, followed by multi-turn reinforcement learning. The RL stage combines hierarchical outcome- and trajectory-level rewards with deviation-aware advantage modulation, jointly addressing reward sparsity and credit assignment challenges in long dialogues. On real customer-service sessions organized into reference cohorts, TRACER-7B surpasses the strongest baseline by 11.4 conversion F1 points, while outperforming all baselines on group-level conversion-rate error and semantic trajectory distance and generalizing to out-of-distribution scenarios. In human Turing tests, annotators identified TRACER conversations at near-chance accuracy. Building on this simulator, we further introduce the Dynamic Marketing Benchmark, which jointly evaluates persuasion and response quality via simulated interactions, revealing that higher response quality does not necessarily correspond to higher conversion rates.

cs.AI↗

Business Taxonomy Construction Using Concept-Level Hierarchical Clustering

Business taxonomies are indispensable tools for investors to do equity research and make professional decisions. However, to identify the structure of industry sectors in an emerging market is challenging for two reasons. First, existing taxonomies are designed for mature markets, which may not be the appropriate classification for small companies with innovative business models. Second, emerging markets are fast-developing, thus the static business taxonomies cannot promptly reflect the new features. In this article, we propose a new method to construct business taxonomies automatically from the content of corporate annual reports. Extracted concepts are hierarchically clustered using greedy affinity propagation. Our method requires less supervision and is able to discover new terms. Experiments and evaluation on the Chinese National Equities Exchange and Quotations (NEEQ) market show several advantages of the business taxonomy we build. Our results provide an effective tool for understanding and investing in the new growth companies.

cs.CL↗