Related papers: CRE-T1 Preview Technical Report: Beyond Contrastiv…

Large reasoning models such as DeepSeek-R1 and OpenAI o1 generate extended chains of thought spanning thousands of tokens, yet their integration with retrieval-augmented generation (RAG) remains fundamentally misaligned. Current RAG systems…

Chain-of-Thought (CoT) reasoning has become a foundation for eliciting multi-step reasoning in large language models, but recent studies show that its benefits do not scale monotonically with chain length: while longer CoT generally enables…

Text classification is a crucial and fundamental task in web content mining. Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the recently proposed supervised contrastive learning approach…

Text embedding models play a crucial role in natural language processing, particularly in information retrieval, and their importance is further highlighted with the recent utilization of RAG (Retrieval- Augmented Generation). This study…

Cross-lingual Cross-modal Retrieval (CCR) is an essential task in web search, which aims to break the barriers between modality and language simultaneously and achieves image-text retrieval in the multi-lingual scenario with a single model.…

Dense retrievers have achieved impressive performance, but their demand for abundant training data limits their application scenarios. Contrastive pre-training, which constructs pseudo-positive examples from unlabeled data, has shown great…

Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning…

We investigate the exploitation of both lexical and neural relevance signals for ad-hoc passage retrieval. Our exploration involves a large-scale training dataset in which dense neural representations of MS-MARCO queries and passages are…

Dense retrieval has become the new paradigm in passage retrieval. Despite its effectiveness on typo-free queries, it is not robust when dealing with queries that contain typos. Current works on improving the typo-robustness of dense…

Intent detection, a critical component in task-oriented dialogue (TOD) systems, faces significant challenges in adapting to the rapid influx of integrable tools with complex interrelationships. Existing approaches, such as zero-shot…

Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored. We introduce ReasonGen-R1, a two-stage framework that first imbues…

How far are Large Language Models (LLMs) in performing deep relational reasoning? In this paper, we evaluate and compare the reasoning capabilities of three cutting-edge LLMs, namely, DeepSeek-R1, DeepSeek-V3 and GPT-4o, through a suite of…

The rapid progress in diffusion-based text-to-image (T2I) generation has created an urgent need for interpretable automatic evaluation methods that can assess the quality of generated images, therefore reducing the human annotation burden.…

As Test-Time Scaling emerges as an active research focus in the large language model community, advanced post-training methods increasingly emphasize extending chain-of-thought (CoT) generation length, thereby enhancing reasoning…

This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance semantic understanding and knowledge scheduling efficiency…

We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which identifies relevant evidence from context, and reasoning are deeply intertwined: retrieval…

Multimodal Large Language Models (MLLMs) have gained significant traction for their ability to process diverse input data types and generate coherent, contextually relevant outputs across various applications. While supervised fine-tuning…

Unsupervised representation learning has recently received lots of interest due to its powerful generalizability through effectively leveraging large-scale unlabeled data. There are two prevalent approaches for this, contrastive learning…

Textbook question answering (TQA) is a complex task, requiring the interpretation of complex multimodal context. Although recent advances have improved overall performance, they often encounter difficulties in educational settings where…

Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning…