English
Related papers

Related papers: When Retrieval Hurts Code Completion: A Diagnostic…

200 papers

Retrieval-augmented generation (RAG) remains brittle on multi-hop questions in realistic deployment settings, where retrieved evidence may be noisy or redundant and only limited context can be passed to the generator. Existing controllers…

Computation and Language · Computer Science 2026-05-08 Yilin Guo , Yinshan Wang , Yixuan Wang

Contextual reasoning with constraints is crucial for enhancing temporal consistency in cross-frame modeling for visual tracking. However, mainstream tracking algorithms typically associate context by merely stacking historical information…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Fansheng Zeng , Bineng Zhong , Haiying Xia , Yufei Tan , Xiantao Hu , Liangtao Shi , Shuxiang Song

Identifying the root cause of a bug remains difficult for many developers because bug reports often lack a bug reproducing test case that reliably triggers the failure. Manually writing such test cases is time-consuming and requires…

Software Engineering · Computer Science 2026-03-10 Zhiwei Fei , Yue Pan , Federica Sarro , Jidong Ge , Marc Liu , Vincent Ng , He Ye

Code intelligence is an emerging domain in software engineering, aiming to improve the effectiveness and efficiency of various code-related tasks. Recent research suggests that incorporating contextual information beyond the basic original…

Software Engineering · Computer Science 2026-02-10 Yanlin Wang , Kefeng Duan , Dewu Zheng , Ensheng Shi , Fengji Zhang , Yanli Wang , Jiachi Chen , Xilin Liu , Yuchi Ma , Hongyu Zhang , Qianxiang Wang , Zibin Zheng

Code completion models have made significant progress in recent years, yet current popular evaluation datasets, such as HumanEval and MBPP, predominantly focus on code completion tasks within a single file. This over-simplified setting…

Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…

Software Engineering · Computer Science 2026-04-16 Jia Feng , Zhanyue Qin , Cuiyun Gao , Ruiqi Wang , Chaozheng Wang , Yingwei Ma , Xiaoyuan Xie

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. However, incorporating a large volume of retrieved documents…

Computation and Language · Computer Science 2026-05-29 Ziqiang Cui , Yunpeng Weng , Xing Tang , Peiyang Liu , Shiwei Li , Bowei He , Jiamin Chen , Yansen Zhang , Xiuqiang He , Chen Ma

Dynamic streams from news feeds, social media, sensor networks, and financial markets challenge static RAG frameworks. Full-scale indices incur high memory costs; periodic rebuilds introduce latency that undermines data freshness; naive…

Information Retrieval · Computer Science 2025-08-11 Yuzhou Zhu

In long-context question answering, selecting the appropriate scope of context for a query remains a key and unresolved challenge. Insufficient context can lead to missing essential information, whereas excessive context often introduces…

Artificial Intelligence · Computer Science 2026-01-22 Siyuan Zhu , Chengdong Xu , Kaiqiang Ke , Chao Yu

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…

Computation and Language · Computer Science 2024-04-09 Pouria Rouzrokh , Shahriar Faghani , Cooper U. Gamble , Moein Shariatnia , Bradley J. Erickson

High Recall Retrieval (HRR), such as eDiscovery and medical systematic review, is a search problem that optimizes the cost of retrieving most relevant documents in a given collection. Iterative approaches, such as iterative relevance…

Information Retrieval · Computer Science 2024-05-08 Eugene Yang

Large language models (LLMs) have the remarkable ability to solve new tasks with just a few examples, but they need access to the right tools. Retrieval Augmented Generation (RAG) addresses this problem by retrieving a list of relevant…

Information Retrieval · Computer Science 2023-12-12 Raviteja Anantha , Tharun Bethi , Danil Vodianik , Srinivas Chappidi

Recent Large Reasoning Models (LRMs) have achieved remarkable progress on task-specific benchmarks, yet their evaluation methods remain constrained by isolated problem-solving paradigms. Existing benchmarks predominantly assess…

Computation and Language · Computer Science 2025-07-16 Zhuoshi Pan , Qizhi Pei , Yu Li , Qiyao Sun , Zinan Tang , H. Vicky Zhao , Conghui He , Lijun Wu

We consider the effect of temporal aggregation on instantaneous (non-temporal) causal discovery in general setting. This is motivated by the observation that the true causal time lag is often considerably shorter than the observational…

Machine Learning · Statistics 2024-09-11 Shunxing Fan , Mingming Gong , Kun Zhang

Retrieval Augmented Generation (RAG) has emerged as a crucial technique for enhancing the accuracy of Large Language Models (LLMs) by incorporating external information. With the advent of LLMs that support increasingly longer context…

Machine Learning · Computer Science 2024-11-07 Quinn Leng , Jacob Portes , Sam Havens , Matei Zaharia , Michael Carbin

Retrieval-Augmented Generation (RAG) is a key approach to mitigating the temporal staleness of large language models (LLMs) by grounding responses in up-to-date evidence. Within the RAG pipeline, re-rankers play a pivotal role in selecting…

Information Retrieval · Computer Science 2026-04-17 Sohyun An , Hayeon Lee , Shuibenyang Yuan , Chun-cheng Jason Chen , Cho-Jui Hsieh , Vijai Mohan , Alexander Min

Retrieval Augmented Generation (RAG) enhances language model performance by incorporating external knowledge retrieved from large corpora, which makes it highly suitable for tasks such as open domain question answering. Standard RAG systems…

Information Retrieval · Computer Science 2025-12-17 Malika Iratni , Mohand Boughanem , Taoufiq Dkaki

Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant information, which could…

Computation and Language · Computer Science 2024-06-18 Jinyuan Fang , Zaiqiao Meng , Craig Macdonald

Large Language Models (LLMs) have demonstrated impressive capabilities in code generation. However, current evaluation datasets suffer from issues such as the lack of runnable test cases, deviation from the distribution of real-world code,…

Software Engineering · Computer Science 2025-08-06 Haiyang Li

Language models significantly benefit from context tokens, such as prompts or scratchpads. They perform better when prompted with informative instructions, and they acquire new reasoning capabilities by generating a scratch-pad before…

Computation and Language · Computer Science 2022-10-03 Charlie Snell , Dan Klein , Ruiqi Zhong