abstract = {This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems. The proposed method first generates pseudo-documents by few-shot prompting large language models (LLMs), and then expands the query with generated pseudo documents. LLMs are trained on web-scale text corpora and are adept at knowledge memorization. The pseudo-documents from LLMs often contain highly relevant information that can aid in query disambiguation and guide the retrievers. Experimental results demonstrate that query2doc boosts the performance of BM25 by 3\% to 15\% on ad-hoc IR datasets, such as MS-MARCO and TREC DL, without any model fine-tuning. Furthermore, our method also benefits state-of-the-art dense retrievers in terms of both in-domain and out-of-domain results.},
urldate = {2026-08-20},
booktitle = {Proceedings of the 2023 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}},
publisher = {Association for Computational Linguistics},
author = {Wang, Liang and Yang, Nan and Wei, Furu},
editor = {Bouamor, Houda and Pino, Juan and Bali, Kalika},
title = {Query {Rewriting} for {Retrieval}-{Augmented} {Large} {Language} {Models}},
url = {http://arxiv.org/abs/2305.14283},
doi = {10.48550/arXiv.2305.14283},
abstract = {Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs from the perspective of the query rewriting. Unlike prior studies focusing on adapting either the retriever or the reader, our approach pays attention to the adaptation of the search query itself, for there is inevitably a gap between the input text and the needed knowledge in retrieval. We first prompt an LLM to generate the query, then use a web search engine to retrieve contexts. Furthermore, to better align the query to the frozen modules, we propose a trainable scheme for our pipeline. A small language model is adopted as a trainable rewriter to cater to the black-box LLM reader. The rewriter is trained using the feedback of the LLM reader by reinforcement learning. Evaluation is conducted on downstream tasks, open-domain QA and multiple-choice QA. Experiments results show consistent performance improvement, indicating that our framework is proven effective and scalable, and brings a new framework for retrieval-augmented LLM.},
urldate = {2026-08-19},
publisher = {arXiv},
author = {Ma, Xinbei and Gong, Yeyun and He, Pengcheng and Zhao, Hai and Duan, Nan},
month = oct,
year = {2023},
note = {arXiv:2305.14283 [cs.CL]},
keywords = {Computer Science - Computation and Language},
}
@article{huang_survey_2025,
title = {A {Survey} on {Hallucination} in {Large} {Language} {Models}: {Principles}, {Taxonomy}, {Challenges}, and {Open} {Questions}},
volume = {43},
issn = {1046-8188, 1558-2868},
shorttitle = {A {Survey} on {Hallucination} in {Large} {Language} {Models}},
url = {https://dl.acm.org/doi/10.1145/3703155},
doi = {10.1145/3703155},
abstract = {The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Nevertheless, LLMs are prone to hallucination, generating plausible yet nonfactual content. This phenomenon raises significant concerns over the reliability of LLMs in real-world information retrieval (IR) systems and has attracted intensive research to detect and mitigate such hallucinations. Given the open-ended general-purpose attributes inherent to LLMs, LLM hallucinations present distinct challenges that diverge from prior task-specific models. This divergence highlights the urgency for a nuanced understanding and comprehensive overview of recent advances in LLM hallucinations. In this survey, we begin with an innovative taxonomy of hallucination in the era of LLM and then delve into the factors contributing to hallucinations. Subsequently, we present a thorough overview of hallucination detection methods and benchmarks. Our discussion then transfers to representative methodologies for mitigating LLM hallucinations. Additionally, we delve into the current limitations faced by retrieval-augmented LLMs in combating hallucinations, offering insights for developing more robust IR systems. Finally, we highlight the promising research directions on LLM hallucinations, including hallucination in large vision-language models and understanding of knowledge boundaries in LLM hallucinations.},
language = {en},
number = {2},
urldate = {2026-08-19},
journal = {ACM Transactions on Information Systems},
author = {Huang, Lei and Yu, Weijiang and Ma, Weitao and Zhong, Weihong and Feng, Zhangyin and Wang, Haotian and Chen, Qianglong and Peng, Weihua and Feng, Xiaocheng and Qin, Bing and Liu, Ting},
month = mar,
year = {2025},
pages = {1--55},
}
@misc{artifex_software_pymupdf4llm_2026,
title = {{PyMuPDF4LLM}: {PDF} {Markdown} {Extraction} for {LLM} workflows},
title = {Seeing {Beyond}: {Enhancing} {Visual} {Question} {Answering} with {Multi}-{Modal} {Retrieval}},
title = {Seeing {Beyond}: {Enhancing} {Visual} {Question} {Answering} with {Multi}-{Modal} {Retrieval}},
...
@@ -151,6 +223,21 @@
...
@@ -151,6 +223,21 @@
year = {2022},
year = {2022},
}
}
@misc{lu_bm25s_2024,
title = {{BM25S}: {Orders} of magnitude faster lexical search via eager sparse scoring},
shorttitle = {{BM25S}},
url = {http://arxiv.org/abs/2407.03618},
doi = {10.48550/arXiv.2407.03618},
abstract = {We introduce BM25S, an efficient Python-based implementation of BM25 that only depends on Numpy and Scipy. BM25S achieves up to a 500x speedup compared to the most popular Python-based framework by eagerly computing BM25 scores during indexing and storing them into sparse matrices. It also achieves considerable speedups compared to highly optimized Java-based implementations, which are used by popular commercial products. Finally, BM25S reproduces the exact implementation of five BM25 variants based on Kamphuis et al. (2020) by extending eager scoring to non-sparse variants using a novel score shifting method. The code can be found at https://github.com/xhluca/bm25s},
urldate = {2026-03-31},
publisher = {arXiv},
author = {Lù, Xing Han},
month = jul,
year = {2024},
note = {arXiv:2407.03618},
keywords = {Computer Science - Computation and Language, Computer Science - Information Retrieval},
}
@inproceedings{parry_mechir_2025,
@inproceedings{parry_mechir_2025,
series = {Lecture {Notes} in {Computer} {Science}},
series = {Lecture {Notes} in {Computer} {Science}},
title = {{MechIR}: {A} {Mechanistic} {Interpretability} {Framework} for {Information} {Retrieval}},
title = {{MechIR}: {A} {Mechanistic} {Interpretability} {Framework} for {Information} {Retrieval}},
