Related papers: Think Harder and Don't Overlook Your Options: Revi…
Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems, offering strong semantic understanding and natural-language reasoning abilities. Despite recent progress, current LLM-based…
Using tools by Large Language Models (LLMs) is a promising avenue to extend their reach beyond language or conversational settings. The number of tools can scale to thousands as they enable accessing sensory information, fetching updated…
During issue resolution, software developers rely on issue reports to discuss solutions for defects, feature requests, and other changes. These discussions contain proposed solutions--from design changes to code implementations--as well as…
Large Language Models (LLMs) have the potential to revolutionize automated traceability by overcoming the challenges faced by previous methods and introducing new possibilities. However, the optimal utilization of LLMs for automated…
With the improving semantic understanding capability of Large Language Models (LLMs), they exhibit a greater awareness and alignment with human values, but this comes at the cost of transparency. Although promising results are achieved via…
As agents operate over long horizons, their memory stores grow continuously, making retrieval critical to accessing relevant information. Many agent queries require reasoning-intensive retrieval, where the connection between query and…
Multi-stage information retrieval (IR) has become a widely-adopted paradigm in search. While Large Language Models (LLMs) have been extensively evaluated as second-stage reranking models for monolingual IR, a systematic large-scale…
The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the…
Large language models (LLMs) are widely applied in chatbots, code generators, and search engines. Workload such as chain-of-throught, complex reasoning, agent services significantly increase the inference cost by invoke the model…
Large language models (LLMs) have revolutionized natural language processing, yet hallucinations in knowledge-intensive tasks remain a critical challenge. Retrieval-augmented generation (RAG) addresses this by integrating external…
While large language models (LLMs) are increasingly deployed as dense retrievers, the impact of their domain-specific specialization on retrieval effectiveness remains underexplored. This investigation systematically examines how…
To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR). However, there still remains a large discrepancy between the…
DeepSeek-V3 and DeepSeek-R1 are leading open-source Large Language Models (LLMs) for general-purpose tasks and reasoning, achieving performance comparable to state-of-the-art closed-source models from companies like OpenAI and Anthropic --…
The effectiveness of multi-stage text retrieval has been solidly demonstrated since before the era of pre-trained language models. However, most existing studies utilize models that predate recent advances in large language models (LLMs).…
Utilizing large language models (LLMs) for document reranking has been a popular and promising research direction in recent years, many studies are dedicated to improving the performance and efficiency of using LLMs for reranking. Besides,…
Large Language Models (LLMs) have demonstrated significant effectiveness across various NLP tasks, including text ranking. This study assesses the performance of large language models (LLMs) in listwise reranking for limited-resource…
Large Language Models (LLMs) have demonstrated superior performance in listwise passage reranking task. However, directly applying them to rank long-form documents introduces both effectiveness and efficiency issues due to the substantially…
Relevance judgments are crucial for evaluating information retrieval systems, but traditional human-annotated labels are time-consuming and expensive. As a result, many researchers turn to automatic alternatives to accelerate method…
Pre-trained deep language models~(LM) have advanced the state-of-the-art of text retrieval. Rerankers fine-tuned from deep LM estimates candidate relevance based on rich contextualized matching signals. Meanwhile, deep LMs can also be…
In knowledge-intensive tasks such as open-domain question answering (OpenQA), large language models (LLMs) often struggle to generate factual answers, relying solely on their internal (parametric) knowledge. To address this limitation,…