Related papers: Learning to Reflect and Correct: Towards Better De…

Retrieval-augmented generation (RAG) improves knowledge-intensive question answering by incorporating external evidence. However, existing RAG methods still suffer from hallucinations and subtle reasoning errors. Recent studies introduce…

Large Language Models (LLMs) have been integrated into recommendation systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant…

Traditional recommendation systems suffer from inconsistency in multi-stage optimization objectives. Generative Recommendation (GR) mitigates them through an end-to-end framework; however, existing methods still rely on matching mechanisms…

In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent…

Text embedding and generative tasks are usually trained separately based on large language models (LLMs) nowadays. This causes a large amount of training cost and deployment effort. Context compression is also a challenging and pressing…

Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-optimize citation fidelity while overlooking relevance to the…

How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by performing iterative latent-state refinement with shared…

Decoding-based regression, which reformulates regression as a sequence generation task, has emerged as a promising paradigm of applying large language models for numerical prediction. However, its progress is hindered by the misalignment…

The dominant retrieve-then-rank pipeline in large-scale recommender systems suffers from mis-calibration and engineering overhead due to its architectural split and differing optimization objectives. While recent generative sequence models…

Recommendation system delivers substantial economic benefits by providing personalized predictions. Generative recommendation (GR) integrates LLMs to enhance the understanding of long user-item sequences. Despite employing attention-based…

Generative recommendation (GR) is an emerging paradigm that tokenizes items into discrete tokens and learns to autoregressively generate the next tokens as predictions. While this token-generation paradigm is expected to surpass traditional…

Growing attention has been paid in Conversational Recommendation System (CRS), which works as a conversation-based and recommendation task-oriented tool to provide items of interest and explore user preference. However, existing work in CRS…

The extensive world knowledge and powerful reasoning capabilities of large language models (LLMs) have attracted significant attention in recommendation systems (RS). Specifically, The chain of thought (CoT) has been shown to improve the…

Recent Large Reasoning Language Models (LRLMs) employ long chain-of-thought reasoning with complex reflection behaviors, typically signaled by specific trigger words (e.g., "Wait" and "Alternatively") to enhance performance. However, these…

Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via…

Collaborative filtering (CF) models have demonstrated remarkable performance in recommender systems, which represent users and items as embedding vectors. Recently, due to the powerful modeling capability of graph neural networks for…

While Large Language Models (LLMs) have revolutionized code generation, standard ``System 1'' approaches that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. Existing iterative…

Harnessing Large Language Models (LLMs) for recommendation systems has emerged as a prominent avenue, drawing substantial research interest. However, existing approaches primarily involve basic prompt techniques for knowledge acquisition,…

Generative retrieval (GR) ranks documents by autoregressively generating document identifiers. Because many GR methods rely on trie-constrained beam search, they are vulnerable to early pruning of relevant prefixes under finite-beam…

Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and reasoning capabilities in favor of static embeddings. We…