arXiv subjects

Cheng cheng

Publications and source records attributed to Cheng cheng.

3 recordsLinked to original sources

arXiv2025

When & How to Write for Personalized Demand-aware Query Rewriting in Video Search

In video search systems, user historical behaviors provide rich context for identifying search intent and resolving ambiguity. However, traditional methods utilizing implicit history features often suffer from signal dilution and delayed feedback. To address these challenges, we propose WeWrite, a novel Personalized Demand-aware Query Rewriting framework. Specifically, WeWrite tackles three key challenges: (1) When to Write: An automated posterior-based mining strategy extracts high-quality samples from user logs, identifying scenarios where personalization is strictly necessary; (2) How to Write: A hybrid training paradigm combines Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO) to align the LLM's output style with the retrieval system; (3) Deployment: A parallel "Fake Recall" architecture ensures low latency. Online A/B testing on a large-scale video platform demonstrates that WeWrite improves the Click-Through Video Volume (VV$>$10s) by 1.07% and reduces the Query Reformulation Rate by 2.97%.

cs.IR↗

arXiv2025

A Comparative Study of Large Language Models and Human Personality Traits

Large Language Models (LLMs) have demonstrated human-like capabilities in language comprehension and generation, becoming active participants in social and cognitive domains. This study investigates whether LLMs exhibit personality-like traits and how these traits compare with human personality, focusing on the applicability of conventional personality assessment tools. A behavior-based approach was used across three empirical studies. Study 1 examined test-retest stability and found that LLMs show higher variability and are more input-sensitive than humans, lacking long-term stability. Based on this, we propose the Distributed Personality Framework, conceptualizing LLM traits as dynamic and input-driven. Study 2 analyzed cross-variant consistency in personality measures and found LLMs' responses were highly sensitive to item wording, showing low internal consistency compared to humans. Study 3 explored personality retention during role-playing, showing LLM traits are shaped by prompt and parameter settings. These findings suggest that LLMs express fluid, externally dependent personality patterns, offering insights for constructing LLM-specific personality frameworks and advancing human-AI interaction. This work contributes to responsible AI development and extends the boundaries of personality psychology in the age of intelligent systems.

cs.CL↗

arXiv2015

Studies on the switching speed effect of the phase shift keying in SLED for generating high power microwave

SLAC energy doubler (SLED) type radio-frequency pulse compressors are widely used in large-scale particle accelerators for converting long-duration moderate-power input pulse into short-duration high-power output pulse. The phase shift keying (PSK) is one of the key components in SLED pulse compression systems. Performance of the PSK will influence the output characteristics of SLED, such as rise-time of the output pulse, the maximal peak power gain, and the energy efficiency. In this paper, high power microwave source based on power combining and pulse compression of conventional klystrons was introduced, the nonideal PSK with slow switching speed and without power output during the switching process were investigated, the experimental results with nonideal PSK agreed well with the analytical results.

physics.acc-ph↗