Related papers: A Technical Report on the Second Place Solution fo…

Proactive intent prediction is a critical capability in modern e-commerce chatbots, enabling "zero-query" recommendations by anticipating user needs from behavioral and contextual signals. However, existing industrial systems face two…

This paper presents a novel approach to address the Entity Recognition and Linking Challenge at NLPCC 2015. The task involves extracting named entity mentions from short search queries and linking them to entities within a reference Chinese…

Finetuned LLMs often exhibit poor uncertainty quantification, manifesting as overconfidence, poor calibration, and unreliable prediction results on test data or out-of-distribution samples. One approach commonly used in vision for…

Large Language Models (LLMs) are increasingly deployed in critical applications requiring reliable reasoning, yet their internal reasoning processes remain difficult to evaluate systematically. Existing methods focus on final-answer…

Large Language Models (LLMs), particularly smaller variants, still struggle with complex reasoning tasks. While inference-time prompting can guide reasoning, existing methods often rely on sequential queries. Ensemble approaches offer a…

Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. Our work aims to improve their efficiency, enabling them to reach high…

Streaming services have reshaped how we discover and engage with digital entertainment. Despite these advancements, effectively understanding the wide spectrum of user search queries continues to pose a significant challenge. An accurate…

Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry. To satisfy the millisecond-level response requirements of online systems while retaining the…

Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG). In this work, we propose a novel instruction fine-tuning framework RankRAG, which instruction-tunes a single LLM for…

With the rapid growth of e-Commerce, online product search has emerged as a popular and effective paradigm for customers to find desired products and engage in online shopping. However, there is still a big gap between the products that…

Large language models (LLMs) achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet often generate unnecessarily long reasoning paths that incur high inference cost. Recent self-consistency-based approaches…

We describe the 1st place winning approach for the CIKM Cup 2016 Challenge. In this paper, we provide an approach to reasonably identify same users across multiple devices based on browsing logs. Our approach regards a candidate ranking…

We propose a two-stage "Mine and Refine" contrastive training framework for semantic text embeddings to enhance multi-category e-commerce search retrieval. Large scale e-commerce search demands embeddings that generalize to long tail, noisy…

Low-Rank Adaptation (LoRA) lowers the computational and memory overhead of fine-tuning large models by updating a low-dimensional subspace of the pre-trained weight matrix. Albeit efficient, LoRA exhibits suboptimal convergence and…

Relevance is a foundation of user experience in e-commerce search. We view relevance optimization as a closed-loop ecosystem involving multiple human roles: users who provide feedback, product managers who define standards, annotators who…

Evaluating LLMs and text-to-image models is a computationally intensive task often overlooked. Efficient evaluation is crucial for understanding the diverse capabilities of these models and enabling comparisons across a growing number of…

Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models (LLMs). To bridge this gap, we propose a two-stage reasoning distillation…

In e-commerce ranking, implicit user feedback is systematically confounded by Position Bias -- the strong propensity of users to interact with top-ranked items regardless of relevance. While Deep Learning architectures (e.g., Two-Tower…

Optimizing industrial search ranking models solely for user engagement signals often introduces systematic biases, prioritizing popular or price-anchored items that may not satisfy semantic intent. We present a production-scale multi-task…

Adaptive Retrieval-Augmented Generation aims to mitigate the interference of extraneous noise by dynamically determining the necessity of retrieving supplementary passages. However, as Large Language Models evolve with increasing robustness…