---
title: "IMRNNs — paper by Saxena et al. (2026) — summary and ideas"
description: "The authors present IMRNNs, a lightweight add-on that works over a frozen encoder. 4.76% recall. 46 references."
authors: ["Yash Saxena", "Ankur Padia", "Kalpa Gunaratna", "Manas Gaur"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: EACL 2026"
source: "https://aclanthology.org/2026.findings-eacl.333/"
doi: "10.18653/v1/2026.findings-eacl.333"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/saxena-2026-imrnns-efficient-method-interpretable-dense/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/saxena-2026-imrnns-efficient-method-interpretable-dense/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/33/) / IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulation

# IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulation

**Authors:** Yash Saxena, Ankur Padia, [Kalpa Gunaratna](https://md.research.elamur.ai/free/en/authors/kalpa-gunaratna/) and [Manas Gaur](https://md.research.elamur.ai/free/en/authors/manas-gaur/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: EACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-eacl.333/) · [PDF](https://aclanthology.org/2026.findings-eacl.333.pdf) · [DOI 10.18653/v1/2026.findings-eacl.333](https://doi.org/10.18653/v1/2026.findings-eacl.333) · [OpenAlex](https://openalex.org/W7140084783)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Dense retrievers in RAG pipelines encode queries and documents into fixed vectors on their own. As a result, a document's representation cannot change depending on the query, and users cannot see why a document was ranked highly. The authors present IMRNNs, a lightweight add-on that works over a frozen encoder. Embeddings are first projected into a smaller working space (256 dimensions for 1024-dimensional inputs). Two small MLP adapters then operate in both directions. One reshapes document embeddings according to the current query. The other adjusts the query using signals from the documents retrieved initially. Because the modulation is a set of explicit affine operations, it can be inspected. The per-dimension change vectors can also be mapped back to vocabulary tokens through a Moore-Penrose pseudoinverse, which surfaces keywords behind ranking shifts. On BEIR datasets, IMRNNs outperforms adapter baselines such as Search-Adaptor, Hypencoder and DIME on average. Scoring still relies on cosine similarity. The work matters because it pairs better retrieval with explanations that are built into the mechanism itself.

## Key points
- The authors report average BEIR improvements over state-of-the-art baselines of +6.35% nDCG, +7.14% recall and +7.04% MRR.
- The evaluation covers seven benchmarks: MS MARCO, Natural Questions, HotpotQA, SciFact, TREC-COVID, FiQA and Webis-Touché. Base encoders include e5-large-v2, MiniLM and BGE.
- The authors describe three kinds of interpretability:
  - **Structural:** the affine weights can be inspected directly.
  - **Attribution-level:** Δq and Δd show which dimensions changed and by how much.
  - **Semantic-level:** back-projection maps changes to tokens, e.g. "Peso" and "Mexico" for relevant documents.
- FiQA results show that IMRNNs depends on the quality of the base embeddings. On top of e5, MiniLM and BGE it trails Hypencoder. When stacked on Hypencoder(8) embeddings, it gains 9.09% nDCG, 4.76% recall and 7.68% MRR.
- The authors list three limitations:
  - token attributions can be noisy;
  - latency grows linearly with corpus size and exceeds that of dimension-selection methods;
  - the method cannot fix weak base embeddings.
- Code is released under CC BY 4.0 at github.com/YashSaxena21/IMRNNs.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works

## Cite

Cite as: Yash Saxena, Ankur Padia, Kalpa Gunaratna and Manas Gaur. 2026. IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulation. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{saxena2026imrnns,
  title = {{IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulation}},
  author = {Yash Saxena, Ankur Padia, Kalpa Gunaratna and Manas Gaur},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.333},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.333}
}
```

- [← previous Improving on State-of-the-Art Models for Sentiment Analysis on Saudi-English Code-Switching Text](https://md.research.elamur.ai/free/en/papers/alghamdi-2026-improving-state-art-models-sentiment/)
- [next → Incorporating Multiword Expressions in Galician Neural Machine Translation: Compositionality, Efficiency, and Performance](https://md.research.elamur.ai/free/en/papers/solla-2026-incorporating-multiword-expressions-galician-neural/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/33/)

## References

46 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, and Been Kim. 2018. Sanity checks for saliency maps. Advances in Neural Information Processing Systems, 31. [find](https://scholar.google.com/scholar?q=Julius+Adebayo%2C+Justin+Gilmer%2C+Michael+Muelly%2C+Ian+Goodfellow%2C+Moritz+Hardt%2C+and+Been+Kim%2E+2018%2E+Sanity+checks+for+saliency+maps%2E+Advances+in+Neural+Information+Processing+Systems%2C+31%2E)
2. Dustin Arendt, Zhuanyi Shaw, Prasha Shrestha, Ellyn Ayton, Maria Glenski, and Svitlana Volkova. 2021. Crosscheck: Rapid, reproducible, and interpretable model evaluation. In Proceedings of the Second Workshop on Data Science with Human in the Loop: Language Advances, pages 79–85. [find](https://scholar.google.com/scholar?q=Dustin+Arendt%2C+Zhuanyi+Shaw%2C+Prasha+Shrestha%2C+Ellyn+Ayton%2C+Maria+Glenski%2C+and+Svitlana+Volkova%2E+2021%2E+Crosscheck%3A+Rapid%2C+reproducible%2C+and+interpretable+model+evaluation%2E+In+Proceedings+of+the+Second+)
3. Akari Asai, Timo Schick, Patrick Lewis, Xilun Chen, Gautier Izacard, Sebastian Riedel, Hannaneh Hajishirzi, and Wen-tau Yih. 2023. [Task-aware retrieval with instructions](https://md.research.elamur.ai/free/en/papers/asai-2023-task-aware-retrieval-instructions/). In Findings of the Association for Computational Linguistics: ACL 2023, pages 3650– 3675, Toronto, Canada. Association for Comput…
4. João Carlos Alves Barata and Mahir Saleh Hussein. 2012. The moore–penrose pseudoinverse: A tutorial review of the theory. Brazilian Journal of Physics, 42(1):146–165. [find](https://scholar.google.com/scholar?q=Jo%C3%A3o+Carlos+Alves+Barata+and+Mahir+Saleh+Hussein%2E+2012%2E+The+moore%E2%80%93penrose+pseudoinverse%3A+A+tutorial+review+of+the+theory%2E+Brazilian+Journal+of+Physics%2C+42%281%29%3A146%E2%80%93165%2E)
5. Nitay Calderon and Roi Reichart. 2025. On behalf of the stakeholders: Trends in nlp model interpretability in the era of llms. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Pa… [find](https://scholar.google.com/scholar?q=Nitay+Calderon+and+Roi+Reichart%2E+2025%2E+On+behalf+of+the+stakeholders%3A+Trends+in+nlp+model+interpretability+in+the+era+of+llms%2E+In+Proceedings+of+the+2025+Conference+of+the+Nations+of+the+Americas+Chap)
6. Cesare Campagnano, Antonio Mallia, and Fabrizio Silvestri. 2025a. Unveiling dime: Reproducibility, generalizability, and formal analysis of dimension importance estimation for dense retrieval. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Re… [find](https://scholar.google.com/scholar?q=Cesare+Campagnano%2C+Antonio+Mallia%2C+and+Fabrizio+Silvestri%2E+2025a%2E+Unveiling+dime%3A+Reproducibility%2C+generalizability%2C+and+formal+analysis+of+dimension+importance+estimation+for+dense+retrieval%2E+In+Proc)
7. Cesare Campagnano, Antonio Mallia, and Fabrizio Silvestri. 2025b. Unveiling dime: Reproducibility, generalizability, and formal analysis of dimension importance estimation for dense retrieval. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Re… [find](https://scholar.google.com/scholar?q=Cesare+Campagnano%2C+Antonio+Mallia%2C+and+Fabrizio+Silvestri%2E+2025b%2E+Unveiling+dime%3A+Reproducibility%2C+generalizability%2C+and+formal+analysis+of+dimension+importance+estimation+for+dense+retrieval%2E+In+Proc)
8. Zhuyun Dai, Vincent Y Zhao, Ji Ma, Yi Luan, Jianmo Ni, Jing Lu, Anton Bakalov, Kelvin Guu, Keith Hall, and Ming-Wei Chang. 2023. [Promptagator: Few-shot dense retrieval from 8 examples](https://md.research.elamur.ai/free/en/papers/dai-2022-promptagator-few-shot-dense-retrieval/). In The Eleventh International Conference on Learning Representations.
9. Ning Ding, Yujia Qin, Guang Yang, Fuchao Wei, Zonghan Yang, Yusheng Su, Shengding Hu, Yulin Chen, Chi-Min Chan, Weize Chen, and 1 others. 2023. [Parameter-efficient fine-tuning of large-scale pre-trained language models](https://md.research.elamur.ai/free/en/papers/ding-2023-parameter-efficient-fine-tuning-large/). Nature machine intelligence, 5(3):220–235.
10. Thibault Formal, Benjamin Piwowarski, and Stéphane Clinchant. 2021. [SPLADE: sparse lexical and expansion model for first stage ranking](https://md.research.elamur.ai/free/en/papers/formal-2021-splade-sparse-lexical-expansion/). In SIGIR ’21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021, pages 2288–…
11. Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Ankita Naik, Pengshan Cai, and Alfio Gliozzo. 2022. [Re2g: Retrieve, rerank, generate](https://md.research.elamur.ai/free/en/papers/glass-2022-re2g-retrieve-rerank-generate/). In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages…
12. Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. [LoRA: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In International Conference on Learning Representations.
13. Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, and Roy Lee. 2023. [LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models](https://md.research.elamur.ai/free/en/papers/hu-2023-llm-adapters-adapter-family-parameter/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing,…
14. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. [Unsupervised dense information retrieval with contrastive learning](https://md.research.elamur.ai/free/en/papers/izacard-2021-unsupervised-dense-information-retrieval-contrastive/). Transactions on Machine Learning Research.
15. Kalervo Järvelin and Jaana Kekäläinen. 2002. Cumulated gain-based evaluation of ir techniques. ACM Transactions on Information Systems (TOIS), 20(4):422–446. [find](https://scholar.google.com/scholar?q=Kalervo+J%C3%A4rvelin+and+Jaana+Kek%C3%A4l%C3%A4inen%2E+2002%2E+Cumulated+gain%2Dbased+evaluation+of+ir+techniques%2E+ACM+Transactions+on+Information+Systems+%28TOIS%29%2C+20%284%29%3A422%E2%80%93446%2E)
16. Hao Kang, Tevin Wang, and Chenyan Xiong. 2025. Interpret and control dense retrieval with sparse latent features. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages… [find](https://scholar.google.com/scholar?q=Hao+Kang%2C+Tevin+Wang%2C+and+Chenyan+Xiong%2E+2025%2E+Interpret+and+control+dense+retrieval+with+sparse+latent+features%2E+In+Proceedings+of+the+2025+Conference+of+the+Nations+of+the+Americas+Chapter+of+the+As)
17. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. [Dense passage retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/karpukhin-2020-dense-passage-retrieval-open-domain/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Onli…
18. Anirudh Khatry, Yasharth Bajpai, Priyanshu Gupta, Sumit Gulwani, and Ashish Tiwari. 2023. Augmented embeddings for custom retrievals. Preprint, arXiv:2310.05380. — [arXiv:2310.05380](https://arxiv.org/abs/2310.05380) [find](https://scholar.google.com/scholar?q=Anirudh+Khatry%2C+Yasharth+Bajpai%2C+Priyanshu+Gupta%2C+Sumit+Gulwani%2C+and+Ashish+Tiwari%2E+2023%2E+Augmented+embeddings+for+custom+retrievals%2E+Preprint%2C+arXiv%3A2310%2E05380%2E+%E2%80%94+%5BarXiv%3A2310%2E05380%5D%28https%3A%2F%2Farxiv%2Eorg)
19. Julian Killingback, Hansi Zeng, and Hamed Zamani. 2025a. Hypencoder: Hypernetworks for information retrieval. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2372–2383. [find](https://scholar.google.com/scholar?q=Julian+Killingback%2C+Hansi+Zeng%2C+and+Hamed+Zamani%2E+2025a%2E+Hypencoder%3A+Hypernetworks+for+information+retrieval%2E+In+Proceedings+of+the+48th+International+ACM+SIGIR+Conference+on+Research+and+Development+)
20. Julian Killingback, Hansi Zeng, and Hamed Zamani. 2025b. Hypencoder: Hypernetworks for information retrieval. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’25, page 2372–2383, New York, NY, USA. Association for Computing Ma… [find](https://scholar.google.com/scholar?q=Julian+Killingback%2C+Hansi+Zeng%2C+and+Hamed+Zamani%2E+2025b%2E+Hypencoder%3A+Hypernetworks+for+information+retrieval%2E+In+Proceedings+of+the+48th+International+ACM+SIGIR+Conference+on+Research+and+Development+)
21. Sejong Kim, Hyunseo Song, Hyunwoo Seo, and Hyunjun Kim. 2025. Optimizing retrieval strategies for financial question answering documents in retrieval-augmented generation systems. arXiv preprint arXiv:2503.15191. — [arXiv:2503.15191](https://arxiv.org/abs/2503.15191) [find](https://scholar.google.com/scholar?q=Sejong+Kim%2C+Hyunseo+Song%2C+Hyunwoo+Seo%2C+and+Hyunjun+Kim%2E+2025%2E+Optimizing+retrieval+strategies+for+financial+question+answering+documents+in+retrieval%2Daugmented+generation+systems%2E+arXiv+preprint+arXiv)
22. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). In Advances in Neural Information Processing Systems, volum…
23. Yizhi Li, Zhenghao Liu, Chenyan Xiong, and Zhiyuan Liu. 2021. More robust dense retrieval with contrastive dual learning. In Proceedings of the 2021 ACM SIGIR International Conference on Theory of Information Retrieval, pages 287–296. [find](https://scholar.google.com/scholar?q=Yizhi+Li%2C+Zhenghao+Liu%2C+Chenyan+Xiong%2C+and+Zhiyuan+Liu%2E+2021%2E+More+robust+dense+retrieval+with+contrastive+dual+learning%2E+In+Proceedings+of+the+2021+ACM+SIGIR+International+Conference+on+Theory+of+Inf)
24. Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin Raffel. 2022a. [Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning](https://md.research.elamur.ai/free/en/papers/liu-2022-few-shot-parameter-efficient-fine/). In Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS ’22, R…
25. Zhenghao Liu, Han Zhang, Chenyan Xiong, Zhiyuan Liu, Yu Gu, and Xiaohua Li. 2022b. Dimension reduction for efficient dense retrieval via conditional autoencoder. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5692–5698, Abu Dhabi, United Arab Emirate… [find](https://scholar.google.com/scholar?q=Zhenghao+Liu%2C+Han+Zhang%2C+Chenyan+Xiong%2C+Zhiyuan+Liu%2C+Yu+Gu%2C+and+Xiaohua+Li%2E+2022b%2E+Dimension+reduction+for+efficient+dense+retrieval+via+conditional+autoencoder%2E+In+Proceedings+of+the+2022+Conference+)
26. Michael Llordes, Debasis Ganguly, Sumit Bhatia, and Chirag Agarwal. 2023a. Explain like i am bm25: Interpreting a dense model’s ranked-list with a sparse approximation. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 1976– 198… [find](https://scholar.google.com/scholar?q=Michael+Llordes%2C+Debasis+Ganguly%2C+Sumit+Bhatia%2C+and+Chirag+Agarwal%2E+2023a%2E+Explain+like+i+am+bm25%3A+Interpreting+a+dense+model%E2%80%99s+ranked%2Dlist+with+a+sparse+approximation%2E+In+Proceedings+of+the+46th+Inte)
27. Michael Llordes, Debasis Ganguly, Sumit Bhatia, and Chirag Agarwal. 2023b. Explain like i am bm25: Interpreting a dense model’s ranked-list with a sparse approximation. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’23, page… [find](https://scholar.google.com/scholar?q=Michael+Llordes%2C+Debasis+Ganguly%2C+Sumit+Bhatia%2C+and+Chirag+Agarwal%2E+2023b%2E+Explain+like+i+am+bm25%3A+Interpreting+a+dense+model%E2%80%99s+ranked%2Dlist+with+a+sparse+approximation%2E+In+Proceedings+of+the+46th+Inte)
28. Xueguang Ma, Minghan Li, Kai Sun, Ji Xin, and Jimmy Lin. 2021. Simple and effective unsupervised redundancy elimination to compress dense vectors for passage retrieval. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2854–2859, Online and Punta Cana,… [find](https://scholar.google.com/scholar?q=Xueguang+Ma%2C+Minghan+Li%2C+Kai+Sun%2C+Ji+Xin%2C+and+Jimmy+Lin%2E+2021%2E+Simple+and+effective+unsupervised+redundancy+elimination+to+compress+dense+vectors+for+passage+retrieval%2E+In+Proceedings+of+the+2021+Conf)
29. Varun Magesh, Faiz Surani, Matthew Dahl, Mirac Suzgun, Christopher D Manning, and Daniel E Ho. 2025. [Hallucination-free? assessing the reliability of leading ai legal research tools](https://md.research.elamur.ai/free/en/papers/magesh-2024-hallucination-free-assessing-reliability-leading/). Journal of Empirical Legal Studies, 22(2):216–242.
30. Monica Munnangi, Akshay Swaminathan, Jason Alan Fries, Jenelle Jindal, Sanjana Narayanan, Ivan Lopez, Lucia Tu, Philip Chung, Jesutofunmi A Omiye, Mehr Kashyap, and 1 others. 2025. Factehr: A dataset for evaluating factuality in clinical notes using llms. [find](https://scholar.google.com/scholar?q=Monica+Munnangi%2C+Akshay+Swaminathan%2C+Jason+Alan+Fries%2C+Jenelle+Jindal%2C+Sanjana+Narayanan%2C+Ivan+Lopez%2C+Lucia+Tu%2C+Philip+Chung%2C+Jesutofunmi+A+Omiye%2C+Mehr+Kashyap%2C+and+1+others%2E+2025%2E+Factehr%3A+A+dataset+)
31. Dheeraj Rajagopal, Vidhisha Balachandran, Eduard H Hovy, and Yulia Tsvetkov. 2021. Selfexplain: A self-explaining architecture for neural text classifiers. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 836– 850. [find](https://scholar.google.com/scholar?q=Dheeraj+Rajagopal%2C+Vidhisha+Balachandran%2C+Eduard+H+Hovy%2C+and+Yulia+Tsvetkov%2E+2021%2E+Selfexplain%3A+A+self%2Dexplaining+architecture+for+neural+text+classifiers%2E+In+Proceedings+of+the+2021+Conference+on+Emp)
32. Stephen Robertson and Hugo Zaragoza. 2009a. The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends in Information Retrieval, 3(4):333–389. [find](https://scholar.google.com/scholar?q=Stephen+Robertson+and+Hugo+Zaragoza%2E+2009a%2E+The+probabilistic+relevance+framework%3A+Bm25+and+beyond%2E+Foundations+and+Trends+in+Information+Retrieval%2C+3%284%29%3A333%E2%80%93389%2E)
33. Stephen Robertson and Hugo Zaragoza. 2009b. The probabilistic relevance framework: Bm25 and beyond. Found. Trends Inf. Retr., 3(4):333–389. [find](https://scholar.google.com/scholar?q=Stephen+Robertson+and+Hugo+Zaragoza%2E+2009b%2E+The+probabilistic+relevance+framework%3A+Bm25+and+beyond%2E+Found%2E+Trends+Inf%2E+Retr%2E%2C+3%284%29%3A333%E2%80%93389%2E)
34. Nicholas Rossi, Juexin Lin, Feng Liu, Zhen Yang, Tony Lee, Alessandro Magnani, and Ciya Liao. 2024. Relevance filtering for embedding-based retrieval. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, CIKM ’24, page 4828–4835, New York, NY, USA. Associa… [find](https://scholar.google.com/scholar?q=Nicholas+Rossi%2C+Juexin+Lin%2C+Feng+Liu%2C+Zhen+Yang%2C+Tony+Lee%2C+Alessandro+Magnani%2C+and+Ciya+Liao%2E+2024%2E+Relevance+filtering+for+embedding%2Dbased+retrieval%2E+In+Proceedings+of+the+33rd+ACM+International+Conf)
35. Hassan Sajjad, Nadir Durrani, and Fahim Dalvi. 2022. [Neuron-level interpretation of deep nlp models: A survey](https://md.research.elamur.ai/free/en/papers/sajjad-2022-neuron-level-interpretation-deep-nlp/). Transactions of the Association for Computational Linguistics, 10:1285–1303.
36. Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A. Smith, Luke Zettlemoyer, and Tao Yu. 2023. [One embedder, any task: Instruction-finetuned text embeddings](https://md.research.elamur.ai/free/en/papers/su-2022-one-embedder-any-task-instruction/). In Findings of the Association for Computational Linguistics: ACL 2023, pages 1102–1121, Toronto…
37. Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, and Jacob Steinhardt. 2023. Interpretability in the wild: a circuit for indirect object identification in GPT-2 small. In The Eleventh International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Kevin+Ro+Wang%2C+Alexandre+Variengien%2C+Arthur+Conmy%2C+Buck+Shlegeris%2C+and+Jacob+Steinhardt%2E+2023%2E+Interpretability+in+the+wild%3A+a+circuit+for+indirect+object+identification+in+GPT%2D2+small%2E+In+The+Elevent)
38. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2024. [Text embeddings by weakly-supervised contrastive pre-training](https://md.research.elamur.ai/free/en/papers/wang-2022-text-embeddings-weakly-supervised-contrastive/). Preprint, arXiv:2212.03533.
39. Jinsung Yoon, Yanfei Chen, Sercan Arik, and Tomas Pfister. 2024a. Search-adaptor: Embedding customization for information retrieval. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12230–12247. [find](https://scholar.google.com/scholar?q=Jinsung+Yoon%2C+Yanfei+Chen%2C+Sercan+Arik%2C+and+Tomas+Pfister%2E+2024a%2E+Search%2Dadaptor%3A+Embedding+customization+for+information+retrieval%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Co)
40. Jinsung Yoon, Yanfei Chen, Sercan Arik, and Tomas Pfister. 2024b. Search-adaptor: Embedding customization for information retrieval. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12230–12247, Bangkok, Thailand. Association f… [find](https://scholar.google.com/scholar?q=Jinsung+Yoon%2C+Yanfei+Chen%2C+Sercan+Arik%2C+and+Tomas+Pfister%2E+2024b%2E+Search%2Dadaptor%3A+Embedding+customization+for+information+retrieval%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Co)
41. Goksenin Yuksel and Jaap Kamps. 2025a. Interpretability analysis of domain adapted dense retrievers. arXiv preprint arXiv:2501.14459. — [arXiv:2501.14459](https://arxiv.org/abs/2501.14459) [find](https://scholar.google.com/scholar?q=Goksenin+Yuksel+and+Jaap+Kamps%2E+2025a%2E+Interpretability+analysis+of+domain+adapted+dense+retrievers%2E+arXiv+preprint+arXiv%3A2501%2E14459%2E+%E2%80%94+%5BarXiv%3A2501%2E14459%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2501%2E14459%29)
42. Goksenin Yuksel and Jaap Kamps. 2025b. Interpretability analysis of domain adapted dense retrievers. Preprint, arXiv:2501.14459. — [arXiv:2501.14459](https://arxiv.org/abs/2501.14459) [find](https://scholar.google.com/scholar?q=Goksenin+Yuksel+and+Jaap+Kamps%2E+2025b%2E+Interpretability+analysis+of+domain+adapted+dense+retrievers%2E+Preprint%2C+arXiv%3A2501%2E14459%2E+%E2%80%94+%5BarXiv%3A2501%2E14459%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2501%2E14459%29)
43. Sepanta Zeighami, Zac Wellmer, and Aditya Parameswaran. 2025. NUDGE: Lightweight non-parametric fine-tuning of embeddings for retrieval. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Sepanta+Zeighami%2C+Zac+Wellmer%2C+and+Aditya+Parameswaran%2E+2025%2E+NUDGE%3A+Lightweight+non%2Dparametric+fine%2Dtuning+of+embeddings+for+retrieval%2E+In+The+Thirteenth+International+Conference+on+Learning+Represen)
44. Sheng Zhang, Jin Wang, Haitao Jiang, and Rui Song. 2022. Locally aggregated feature attribution on natural language model understanding. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2189–2201. [find](https://scholar.google.com/scholar?q=Sheng+Zhang%2C+Jin+Wang%2C+Haitao+Jiang%2C+and+Rui+Song%2E+2022%2E+Locally+aggregated+feature+attribution+on+natural+language+model+understanding%2E+In+Proceedings+of+the+2022+Conference+of+the+North+American+Cha)
45. Yilun Zhou, Serena Booth, Marco Tulio Ribeiro, and Julie Shah. 2022. Do feature attribution methods correctly attribute features? In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 9623–9633. [find](https://scholar.google.com/scholar?q=Yilun+Zhou%2C+Serena+Booth%2C+Marco+Tulio+Ribeiro%2C+and+Julie+Shah%2E+2022%2E+Do+feature+attribution+methods+correctly+attribute+features%3F+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volu)
46. Yujia Zhou, Yan Liu, Xiaoxi Li, Jiajie Jin, Hongjin Qian, Zheng Liu, Chaozhuo Li, Zhicheng Dou, Tsung-Yi Ho, and Philip S Yu. 2024. Trustworthiness in retrieval-augmented generation systems: A survey. arXiv preprint arXiv:2409.10102. — [arXiv:2409.10102](https://arxiv.org/abs/2409.10102) [find](https://scholar.google.com/scholar?q=Yujia+Zhou%2C+Yan+Liu%2C+Xiaoxi+Li%2C+Jiajie+Jin%2C+Hongjin+Qian%2C+Zheng+Liu%2C+Chaozhuo+Li%2C+Zhicheng+Dou%2C+Tsung%2DYi+Ho%2C+and+Philip+S+Yu%2E+2024%2E+Trustworthiness+in+retrieval%2Daugmented+generation+systems%3A+A+survey%2E)

*Updated 1 November 2026*