arXiv subjects

Zhiheng Qin

Publications and source records attributed to Zhiheng Qin.

6 recordsLinked to original sources

arXiv2026

Scaling Properties of Same-Family On-Policy Distillation

*Reinforcement learning (RL)* can induce substantial reasoning capabilities in large language models (LLMs), but how much of this capability transfers across model scales, and how quickly, remains unclear. We study the scaling properties of *on-policy distillation (OPD)* across *weak-to-strong*, *same-base*, and *strong-to-weak* teacher--student setups. We find that early OPD training dynamics uniformly exhibit a regular *useful-transfer* regime, in which held-out accuracy (the *gold score*, $G$) rises approximately linearly in $d=\sqrt{\mathrm{KL}(π_θ\Vert π_{\mathrm{ref}})}$, the square root of token-level reverse KL divergence from the student initialization. In every observed weak-to-strong pair, the student's peak gold score exceeds its teacher's own, so a compact RL expert can transfer capability to a much larger student via OPD. To estimate OPD outcomes, we fit *power laws* for how $G_{\mathrm{peak}}$ and the slope of the useful-transfer regime scale with student and teacher parameter counts and with teacher gold score. These laws show that peak gold score improves with teacher scale only up to roughly the student's scale, and that at a matched gold score smaller teachers transfer better, so a teacher's score alone does not define its supervision value. We also study the scaling effects of two OPD variants, bootstrapping weak-to-strong OPD, and the degree of on-policy supervision.

cs.LG↗

arXiv2026

REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs

Large Language Models (LLMs) are increasingly expected to interact with users over long time horizons. However, due to their finite context window, LLMs cannot retain all past interactions, making long-term memory management essential for storing, updating, and retrieving historical information beyond the context limit. Although recent memory systems attempt to address this issue by storing historical information externally, existing approaches suffer from three key limitations: flat text-based memory organizations fail to capture explicit relations among memories, structured memory systems often destructively overwrite evolving facts, and current retrieval mechanisms remain query-agnostic and passive when evidence is incomplete. REAL constructs long-term conversational memory as a temporal and confidence-aware directed property graph, where each atomic fact is represented with entities, relations, valid-time intervals, confidence scores, and exploration intent labels. During memory construction, REAL adopts a non-destructive temporal update strategy that preserves parallel fact versions and their validity intervals, enabling faithful tracking of fact evolution. During retrieval, REAL anchors query-relevant root entities, decouples their exploration intents, and performs semantic evaluator-guided hybrid beam search to extract compact memory subgraphs. It further incorporates counterfactual inference to repair unreliable retrieval states and recover missing memory evidence through implicit logical relations. Comprehensive experiments demonstrate that REAL substantially improves long-term memory performance over flat-text, graph-based, and existing memory baselines, achieving an average improvement of 22.72\%.

cs.CL↗

arXiv2025

CroPS: Improving Dense Retrieval with Cross-Perspective Positive Samples in Short-Video Search

Dense retrieval has become a foundational paradigm in modern search systems, especially on short-video platforms. However, most industrial systems adopt a self-reinforcing training pipeline that relies on historically exposed user interactions for supervision. This paradigm inevitably leads to a filter bubble effect, where potentially relevant but previously unseen content is excluded from the training signal, biasing the model toward narrow and conservative retrieval. In this paper, we present CroPS (Cross-Perspective Positive Samples), a novel retrieval data engine designed to alleviate this problem by introducing diverse and semantically meaningful positive examples from multiple perspectives. CroPS enhances training with positive signals derived from user query reformulation behavior (query-level), engagement data in recommendation streams (system-level), and world knowledge synthesized by large language models (knowledge-level). To effectively utilize these heterogeneous signals, we introduce a Hierarchical Label Assignment (HLA) strategy and a corresponding H-InfoNCE loss that together enable fine-grained, relevance-aware optimization. Extensive experiments conducted on Kuaishou Search, a large-scale commercial short-video search platform, demonstrate that CroPS significantly outperforms strong baselines both offline and in live A/B tests, achieving superior retrieval performance and reducing query reformulation rates. CroPS is now fully deployed in Kuaishou Search, serving hundreds of millions of users daily.

cs.IR↗

arXiv2025

UniDex: Rethinking Search Inverted Indexing with Unified Semantic Modeling

Inverted indexing has traditionally been a cornerstone of modern search systems, leveraging exact term matches to determine relevance between queries and documents. However, this term-based approach often emphasizes surface-level token overlap, limiting the system's generalization capabilities and retrieval effectiveness. To address these challenges, we propose UniDex, a novel model-based method that employs unified semantic modeling to revolutionize inverted indexing. UniDex replaces complex manual designs with a streamlined architecture, enhancing semantic generalization while reducing maintenance overhead. Our approach involves two key components: UniTouch, which maps queries and documents into semantic IDs for improved retrieval, and UniRank, which employs semantic matching to rank results effectively. Through large-scale industrial datasets and real-world online traffic assessments, we demonstrate that UniDex significantly improves retrieval capabilities, marking a paradigm shift from term-based to model-based indexing. Our deployment within Kuaishou's short-video search systems further validates UniDex's practical effectiveness, serving hundreds of millions of active users efficiently.

cs.IR↗

arXiv2025

UniSearch: Rethinking Search System with a Unified Generative Architecture

Modern search systems play a crucial role in facilitating information acquisition. Traditional search engines typically rely on a cascaded architecture, where results are retrieved through recall, pre-ranking, and ranking stages. The complexity of designing and maintaining multiple modules makes it difficult to achieve holistic performance gains. Recent advances in generative recommendation have motivated the exploration of unified generative search as an alternative. However, existing approaches are not genuinely end-to-end: they typically train an item encoder to tokenize candidates first and then optimize a generator separately, leading to objective inconsistency and limited generalization. To address these limitations, we propose UniSearch, a unified generative search framework for Kuaishou Search. UniSearch replaces the cascaded pipeline with an end-to-end architecture that integrates a Search Generator and a Video Encoder. The Generator produces semantic identifiers of relevant items given a user query, while the Video Encoder learns latent item embeddings and provides their tokenized representations. A unified training framework jointly optimizes both components, enabling mutual enhancement and improving representation quality and generation accuracy. Furthermore, we introduce Search Preference Optimization (SPO), which leverages a reward model and real user feedback to better align generation with user preferences. Extensive experiments on industrial-scale datasets, together with online A/B testing in both short-video and live search scenarios, demonstrate the strong effectiveness and deployment potential of UniSearch. Notably, its deployment in live search yields the largest single-experiment improvement in recent years of our product's history, highlighting its practical value for real-world applications.

cs.IR↗

arXiv2025

Personalized Query Auto-Completion for Long and Short-Term Interests with Adaptive Detoxification Generation

Query auto-completion (QAC) plays a crucial role in modern search systems. However, in real-world applications, there are two pressing challenges that still need to be addressed. First, there is a need for hierarchical personalized representations for users. Previous approaches have typically used users' search behavior as a single, overall representation, which proves inadequate in more nuanced generative scenarios. Additionally, query prefixes are typically short and may contain typos or sensitive information, increasing the likelihood of generating toxic content compared to traditional text generation tasks. Such toxic content can degrade user experience and lead to public relations issues. Therefore, the second critical challenge is detoxifying QAC systems. To address these two limitations, we propose a novel model (LaD) that captures personalized information from both long-term and short-term interests, incorporating adaptive detoxification. In LaD, personalized information is captured hierarchically at both coarse-grained and fine-grained levels. This approach preserves as much personalized information as possible while enabling online generation within time constraints. To move a futher step, we propose an online training method based on Reject Preference Optimization (RPO). By incorporating a special token [Reject] during both the training and inference processes, the model achieves adaptive detoxification. Consequently, the generated text presented to users is both non-toxic and relevant to the given prefix. We conduct comprehensive experiments on industrial-scale datasets and perform online A/B tests, delivering the largest single-experiment metric improvement in nearly two years of our product. Our model has been deployed on Kuaishou search, driving the primary traffic for hundreds of millions of active users. The code is available at https://github.com/JXZe/LaD.

cs.CL↗