中文
相关论文

相关论文: Prism-Reranker: Beyond Relevance Scoring -- Jointl…

200 篇论文

Large Language Models (LLMs) are becoming essential tools for various natural language processing tasks but often suffer from generating outdated or incorrect information. Retrieval-Augmented Generation (RAG) addresses this issue by…

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…

计算与语言 · 计算机科学 2024-03-29 Soyeong Jeong , Jinheon Baek , Sukmin Cho , Sung Ju Hwang , Jong C. Park

Large language models (LLMs) are increasingly used to support question answering and decision-making in high-stakes, domain-specific settings such as natural hazard response and infrastructure planning, where effective answers must convey…

计算与语言 · 计算机科学 2026-02-11 Homaira Huda Shomee , Rochana Chaturvedi , Yangxinyu Xie , Tanwi Mallick

Retrieval-Augmented Generation (RAG) grounds large language models (LLMs) in external evidence, but fails when retrieved sources conflict or contain outdated or subjective information. Prior work address these issues independently but lack…

计算与语言 · 计算机科学 2025-12-19 Shubham Mishra , Samyek Jain , Gorang Mehrishi , Shiv Tiwari , Harsh Sharma , Pratik Narang , Dhruv Kumar

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which…

计算与语言 · 计算机科学 2026-02-03 Poushali Sengupta , Shashi Raj Pandey , Sabita Maharjan , Frank Eliassen

The LLM-as-judge paradigm is increasingly being adopted for automated evaluation of model outputs. While LLM judges have shown promise on constrained evaluation tasks, closed source LLMs display critical shortcomings when deployed in real…

计算与语言 · 计算机科学 2024-12-24 Darshan Deshpande , Selvan Sunitha Ravi , Sky CH-Wang , Bartosz Mielczarek , Anand Kannappan , Rebecca Qian

Large language models (LLMs) serve as an active and promising field of generative artificial intelligence and have demonstrated abilities to perform complex tasks in multiple domains, including mathematical and scientific reasoning. In this…

人工智能 · 计算机科学 2026-03-03 Ao Cheng , Lei Zhang , Guowei He

Recent advances in large language models (LLMs) have inspired new paradigms for document reranking. While this paradigm better exploits the reasoning and contextual understanding capabilities of LLMs, most existing LLM-based rerankers rely…

信息检索 · 计算机科学 2026-02-16 Qi Liu , Kun Ai , Jiaxin Mao , Yanzhao Zhang , Mingxin Li , Dingkun Long , Pengjun Xie , Fengbin Zhu , Ji-Rong Wen

LLMs have demonstrated impressive proficiency in generating coherent and high-quality text, making them valuable across a range of text-generation tasks. However, rigorous evaluation of this generated content is crucial, as ensuring its…

This study develops a question-answering system based on Retrieval-Augmented Generation (RAG) using Chinese Wikipedia and Lawbank as retrieval sources. Using TTQA and TMMLU+ as evaluation datasets, the system employs BGE-M3 for dense vector…

信息检索 · 计算机科学 2025-01-17 Te-Lun Yang , Jyi-Shane Liu , Yuen-Hsien Tseng , Jyh-Shing Roger Jang

Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning over the retrieved information, with no clear or…

信息检索 · 计算机科学 2026-04-10 Roxana Petcu , Evangelos Kanoulas , Maarten de Rijke

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…

计算与语言 · 计算机科学 2024-07-03 Yue Yu , Wei Ping , Zihan Liu , Boxin Wang , Jiaxuan You , Chao Zhang , Mohammad Shoeybi , Bryan Catanzaro

Retrieval-augmented language models (RALMs) represent a substantial advancement in the capabilities of large language models, notably in reducing factual hallucination by leveraging external knowledge sources. However, the reliability of…

计算与语言 · 计算机科学 2024-10-04 Wenhao Yu , Hongming Zhang , Xiaoman Pan , Kaixin Ma , Hongwei Wang , Dong Yu

Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are…

Evaluation of search engines relies on assessments of search results for selected test queries, from which we would ideally like to draw conclusions in terms of relevance of the results for general (e.g., future, unknown) users. In practice…

信息检索 · 计算机科学 2015-11-24 Thomas Demeester , Robin Aly , Djoerd Hiemstra , Dong Nguyen , Chris Develder

Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to…

计算与语言 · 计算机科学 2024-10-08 Tao Tan , Yining Qian , Ang Lv , Hongzhan Lin , Songhao Wu , Yongbo Wang , Feng Wang , Jingtong Wu , Xin Lu , Rui Yan

In enterprise search, building high-quality datasets at scale remains a central challenge due to the difficulty of acquiring labeled data. To resolve this challenge, we propose an efficient approach to fine-tune small language models (SLMs)…

With the rapid growth of scientific literature, scientific question answering (SciQA) has become increasingly critical for exploring and utilizing scientific knowledge. Retrieval-Augmented Generation (RAG) enhances LLMs by incorporating…

计算与语言 · 计算机科学 2026-01-26 Haotian Chen , Qingqing Long , Siyu Pu , Xiao Luo , Wei Ju , Meng Xiao , Yuanchun Zhou , Jianghua Zhao , Xuezhi Wang

Retrieve-and-rerank is a popular retrieval pipeline because of its ability to make slow but effective rerankers efficient enough at query time by reducing the number of comparisons. Recent works in neural rerankers take advantage of large…

信息检索 · 计算机科学 2025-05-21 Eugene Yang , Andrew Yates , Kathryn Ricci , Orion Weller , Vivek Chari , Benjamin Van Durme , Dawn Lawrie

Recent advances in large language models (LLMs) have propelled research in natural language interfaces to databases. However, most state-of-the-art text-to-SQL systems still depend on complex, multi-stage pipelines. This work proposes a…

人工智能 · 计算机科学 2025-06-03 Fernando Granado , Roberto Lotufo , Jayr Pereira
‹ 上一页 1 8 9 10 下一页 ›