Related papers: Reproducing Complex Set-Compositional Information …

In tasks like semantic parsing, instruction following, and question answering, standard deep networks fail to generalize compositionally from small datasets. Many existing approaches overcome this limitation with model architectures that…

Large Language Models (LLMs) have demonstrated significant potential in medical Question Answering (QA), yet they remain prone to hallucinations and ungrounded reasoning, limiting their reliability in high-stakes clinical scenarios. While…

Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…

Information retrieval (IR) in dynamic data streams is a crucial task, as shifts in data distribution degrade the performance of AI-powered IR systems. To mitigate this issue, memory-based continual learning has been widely adopted for IR.…

Retrieve-and-rerank is a prevalent framework in neural information retrieval, wherein a bi-encoder network initially retrieves a pre-defined number of candidates (e.g., K=100), which are then reranked by a more powerful cross-encoder model.…

Conversational search aims to satisfy users' complex information needs via multiple-turn interactions. The key challenge lies in revealing real users' search intent from the context-dependent queries. Previous studies achieve conversational…

Query reformulation is a well-known problem in Information Retrieval (IR) aimed at enhancing single search successful completion rate by automatically modifying user's input query. Recent methods leverage Large Language Models (LLMs) to…

DeepSeek-R1, known for its low training cost and exceptional reasoning capabilities, has achieved state-of-the-art performance on various benchmarks. However, detailed evaluations for DeepSeek Series models from the perspective of…

Retrieval-Augmented Generation (RAG) is a powerful technique for enriching Large Language Models (LLMs) with external knowledge, allowing for factually grounded responses, a critical requirement in high-stakes domains such as healthcare.…

Large language models are powerful text processors and reasoners, but are still subject to limitations including outdated knowledge and hallucinations, which necessitates connecting them to the world. Retrieval-augmented large language…

Reasoning-intensive retrieval aims to surface evidence that supports downstream reasoning rather than merely matching topical similarity. This capability is increasingly important for agentic search systems, where retrievers must provide…

Neural retrievers are effective but brittle: underspecified or ambiguous queries can misdirect ranking even when relevant documents exist. Existing approaches address this brittleness only partially: LLMs rewrite queries without retriever…

In analyzing vast amounts of digitally stored historical image data, existing content-based retrieval methods often overlook significant non-semantic information, limiting their effectiveness for flexible exploration across varied themes.…

Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of retrieved context. While retrieval-augmented generation…

In-context learning (ICL), teaching a large language model (LLM) to perform a task with few-shot demonstrations rather than adjusting the model parameters, has emerged as a strong paradigm for using LLMs. While early studies primarily used…

E-commerce recommendation and search commonly rely on sparse keyword matching (e.g., BM25), which breaks down under vocabulary mismatch when user intent has limited lexical overlap with product metadata. We cast content-based recommendation…

Question-answering (QA) is an important application of Information Retrieval (IR) and language models, and the latest trend is toward pre-trained large neural networks with embedding parameters. Augmenting QA performances with these LLMs…

Retrieval-Augmented Large Language Models (LLMs), which incorporate the non-parametric knowledge from external knowledge bases into LLMs, have emerged as a promising approach to enhancing response accuracy in several tasks, such as…

Retrieval-Augmented Generation (RAG) encounters efficiency challenges when scaling to massive knowledge bases while preserving contextual relevance. We propose Hash-RAG, a framework that integrates deep hashing techniques with systematic…

Existing summarization systems mostly generate summaries purely relying on the content of the source document. However, even for humans, we usually need some references or exemplars to help us fully understand the source document and write…