Information Retrieval · arXiv:2611.16488 v1 · submitted 12 Nov 2026 · 44 references
Active Learning of Approximate LLM Ranking for Energy-Efficient Retrieval of Long Queries
The paper says
“Search engines and Large Language Models (LLMs) offer complementary strengths for document retrieval: lexical retrievers which rely on keyword matching are fast and energy-efficient, whereas LLMs capture semantic meaning and excel at interpreting long, context-rich queries.”
more of the abstract
However, this comes at a cost that is computationally and energetically prohibitive. We propose the LLM Active Approximation Model (LAAM), a hybrid retrieval framework that introduces a lightweight learned predictor which serves as an intermediary between semantic retrieval and LLM retrieval. LAAM is refined through an active learning loop where an LLM labels a small number of documents. By concentrating LLM evaluations on the most informative documents, the framework substantially reduces inference cost while preserving retrieval effectiveness. We evaluate the proposed framework on TREC Robust 2004 using Lucene with BM25 retrieval and DeepSeek v3 as the LLM, under three levels of query verbosity. For verbose queries, LAAM achieves 87% of average P@10 achieved by DeepSeek's reranking (0.459 vs. 0.526), while requiring only 3.3% of the per-query energy consumption. LAAM is statistically significantly better than BM25 and is indistinguishable from DeepSeek on average precision, though not on MAP (Friedman test, P<0.05 with post-hoc testing). Overall, our results demonstrate that selectively approximating LLM relevance judgments through active learning enables retrieval accuracy to be controlled directly through the evaluation (and consequently energy) budget. Rather than committing to either inexpensive (and less accurate) lexical retrieval or exhaustive (and expensive) LLM reranking, our framework exposes a continuous spectrum of operating points along the energy–accuracy curve, allowing practitioners to select how to trade retrieval quality with computational budget.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person
It can be wrong. Challenge this review or reply to it.
Holds up, with conditions. A practical active learning framework for approximating LLM ranks with clear energy-accuracy trade-offs; "surpasses" claim needs softening. This line is wrong
3 major objections · 5 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 44 references say.
The paper says, at §4.2.6, §5.2, Abstract
The review did not quote this passage.
Pith says: Objection 1 of 3 · major
The central efficiency claim—that LAAM consumes only 3.3% of the energy of full DeepSeek reranking—rests on an estimated rather than directly measured energy cost for DeepSeek. The authors acknowledge this limitation in §6 but the abstract and conclusions present the figure without the necessary caveat.
more of objection 1
Moreover, the paper does not clarify whether the energy measurements of the LAAM pipeline include the cost of (re)training the Gradient Boosting model at each iteration. If retraining is not included, the reported energy for LAAM is an underestimate. Please either provide direct measurements, expand the sensitivity analysis of the estimation, or qualify the 3.3% figure prominently, and specify whether model training energy is accounted for.
The paper says, at §6, lines [b242–b245]
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.71):
“Testing the framework on newer or private collections that are less likely to overlap with LLM training data would provide stronger evidence that the observed gains generalize beyond this benchmark.”
Pith says: Objection 2 of 3 · major
The authors acknowledge that TREC Robust 2004 may be in DeepSeek's training data, so some relevance judgments may reflect memorization rather than inference. They mitigate this by noting that on short queries LAAM does not consistently beat BM25. However, this does not rule out selective memorization for verbose narrative queries—the very setting where the claim of LLM superiority is largest.
more of objection 2
If DeepSeek's advantage over BM25 on narrative queries is partially artifactual, then LAAM's ability to recoup 87% of that advantage becomes less meaningful. The authors should discuss the magnitude of this risk more thoroughly and, if possible, provide evidence (e.g., a subcorpus analysis or evaluation on a collection not seen by DeepSeek) that the gains reflect genuine semantic reasoning.
The paper says, at Table 1, Abstract, line [b218]
The review did not quote this passage.
Pith says: Objection 3 of 3 · major
The abstract states LAAM is statistically indistinguishable from DeepSeek on average precision, and the strongest claim (b218) says LAAM 'in some cases surpasses [exhaustive LLM reranking].' While for narrative P@1 at K=50 LAAM is numerically higher (0.771 vs 0.674), the post-hoc tests confirm the difference is not stastically significant (the paper itself says LAAM is indistinguishable). The word 'surpasss' is therefore misleading. Please revise to indicate that apparent advantages are not stastically significant.
5 minor objections
The paper says, at §2.5
Pith says: minor objection 1 of 5
The positioning relative to BAGEL and TS-SetRank is useful, but it would be clearer to explicitly state that LAAM is the only one that learns a lightweight surrogate predictor, while the others address sampling or block selection.
The paper says, at Table 1
Pith says: minor objection 2 of 5
Reporting the Frriedman test p-values is appropriate, but consider including the p-values of the post-hoc pairwise comparisons (or a letter superscript) directly in the table for eader reference.
show 3 more
The paper says, at §4.2.1
Pith says: minor objection 3 of 5
The parameters of the initial sampling strategies (e.g., a,b,c,β) are described as 'chosen arbitrarily.' A brief note on whether the conclusions are sensitive to these choices would be helpful.
The paper says, at Figure 2
Pith says: minor objection 4 of 5
The x-axis is logarithmic; ensure the axis labels and ticks are clearly legible in black-and-white printing.
The paper says, at Appendix A
Pith says: minor objection 5 of 5
The prompt used for DeepSeek is given; consider adding a note on whether the same prompt structure was used uniformly for all three query verbosity levels (title, description, narrative).
What would settle it
Replicate the main experiment (narrative queries, K=50 and K=100) on a dataset whose documents and relevance judgments post-date DeepSeek's training cutoff (e.g., TREC 2023 or a private collection). If the P@10 gap between DeepSeek and BM25 narrows significantly compared to Table 1, then the generalizabillity of LAAM's gains is weakened. If the gap remains comparable, the memorization concern is mostly dismmissed for the current result.
from the skeptic's reading
How the review went
4 readings by deepseek-v4-flash · 13 Nov 2026
- Reader holds up, with conditions
- Skeptic partly agrees
- Editor wrote the verdict above
- Referee major revision: 3 major objections, 5 minor
Not run on this paper: the simulated authors' defence.
Pith did not check this review's objections against the paper.
The review in full
The review in brief, machine-written
This is a solid, well-executed empirical study. The core idea — train a gradient boosting surrogate to predict LLM relevance scores, using disagreement with BM25 to guide labelling — is not a paradigm shift but the implementation and evaluation are thorough. The novelty lies in combining disagreement-based active learning with a lightweight learned predictor, whereas prior work (BAGEL, TS-SetRank) focussed on sampling for the LLLM rather than learning a surrogate.
The paper's main strength is the extensive ablation: initial sampling strategies, feature sets, embedding models, selection policies. The central result — 87% of DeepSeek's P@10 at 3.3% of its energy on narrative queires — is clearly supported by diminishing returns. The direct energy measurement for their own pipeline (perf) and the use of a published estimation method for DeepSeek are appropriate.
Soft spots are few but real. First, the claim that LAAM 'surpasses' full DeepSeek in some cases is not backed by the stats: they report 'indistinguishability' on P@1 and P@10, and DeepSeek is significantly better on MAP. The word 'surpasses' shold be removed or reserved for cases with proper support. Second, the energy figure for DeepSeek is estimated, not measured, so the exact 3.3% is approximate; the authors acknowledge this but it should be highlighted in any refereed version. Third, the memorization concern (DeepSeek may have seen TREC during training) is acknowledged and partially mitgated by the null results on short queires, but it remains an open question on truly unseen data — exactly as the authors state in their limitations.
Overall this is a useful contribution for ther IR community, giving practitioner a concrete method to trade accuracy for energy. It should be acceptedf or peer review after toning down the 'surpasses' claim. I would probably cite it as a state-of-the-art baseline for active learning in retrieval.
The strongest objection
The central claim rests on DeepSeek being a genuinely superior ranking function whose judgments LAAM can efficiently approximate. However, DeepSeek's training data may include the queries and documents of TREC Robust 2004, as the authors acknowledge (Section 6, [b242-b245]). If DeepSeek's relevance scores reflect memorized patterns rather than pure inference, the apparent gain over BM25 on narrative queries where the gap is largest could be partially artifactual. The authors mitigate by noting that on short queries LAAM does not consistently beat BM25, but this does not rule out selective memorization for verbose queries that more closely resemble training examples. If the advantage of exhaustive DeepSeek reranking shrinks on a corpus not seen during training, then LAAM's ability to recoup 87% of that advantage would also shrink, and the system's value as a general solution would be weakened. This is load-bearing because it questions whether the fundamental premise (that the LLM is a semantically superior ranker for long queries) holds on genuinely unseen data.
The reader's weakest_assumption focused on the greedy selection policy lacking theoretical guarantee. However, the empirical comparisons (Table 2, Figure 6) show that the greedy policy outperforms alternatives, so this is not the most fragile point. A more fundamental concern is the potential memorization in the LLM's relevance judgments due to training data overlap. The paper acknowledges this limitation (b242-b245) but does not fully resolve it. If the LLM's advantage on narrative queries is partly memorization, then LAAM's performance which approximates those potentially inflated judgments may not generalize. This is load-bearing because the central claim (b218) directly depends on the LLM being a superior ranker that LAAM can efficiently approximate. The suggested test (repeat on a post-cutoff dataset) would directly assess whether the observed gains are robust or rely on memorization. The reader's verdict of CONDITIONAL already acknowledges concerns; this test is a concrete way to satisfy that condition. No change to the verdict is necessary, as the condition remains appropriate.
The referee's report
The problem of making LLM-based retrieval computationally feasible is timely and important. LAAM offers a pragmatic approach by learning a surrogate model that concentrates LLM evaluations on informative documents, exposing a continuous energy-accuracy trade-off. The evaluation includes statistical tests and ablation studies, and the energy measurements are partially hardware-measured. If the reported energy savings are robust, the framework could enable cost-aware retrieval for long queries, a scenario where LLMs provide the clearest semantic advantage but have been prohibitive.
Pith's reading of the paper (a machine's summary, not the authors')
The paper tries to establish that a retrieval system can approach the accuracy of an expensive large language model (LLM) reranker by actively learning a cheap surrogate predictor that approximates the LLM's relevance judgments. The key insight is that most documents in a candidate list do not need to be evaluated by the LLM; a small, strategically chosen set suffices to train a model that reorders the rest. The authors demonstrate on TREC Robust 2004 using DeepSeek as the LLM that for verbose narrative queries the surrogate achieves 87% of the full reranker's precision at 10 while consuming only 3.3% of the per-query energy. The method exposes a continuous energy–accuracy tradeoff, allowing practitioners to adjust the number of LLM evaluations to fit a computational budget.
What carries the argument. The LLM Active Approximation Model (LAAM): a gradient boosting regressor that predicts an LLM's relevance score (1–1000) from a feature vector combining TF-IDF cosine similarity, query-term overlap, and sentence-transformer embeddings of the query and document. During active learning, the system selects the document with the largest absolute difference between its predicted LAAM score and its BM25 score (greedy disagreement), labels it with the LLM, and incrementally retrains the model. This pure-exploitation policy concentrates LLM effort on documents where lexical and semantic signals diverge most.
Core claim. The central claim is that a gradient-boosting regression model, trained on a small number of LLM-labeled documents selected by a greedy disagreement-based active learning policy, can approximate the ranking of an exhaustive LLM reranker well enough to yield statistically indistinguishable precision at 1 and 10 for verbose queries, while cutting energy consumption by over 95%. The paper shows that this holds across three query verbosity levels, with the largest gains on long narrative queries where lexical retrieval is weakest. The energy–accuracy curve exhibits strong diminishing returns, meaning most improvements come from the first few dozen LLM evaluations.
The premise it rests on. The greedy document selection policy, which always picks the document with the largest difference between the predicted LAAM score and the BM25 score, assumes that this disagreement signal is the most informative criterion for reducing surrogate error; no theoretical guarantee or empirical comparison to uncertainty-based sampling is provided.
If the paper is right (Pith's inferences, not the authors')
Retrieval systems can treat the number of LLM evaluations as a tunable resource, enabling a smooth transition from cheap lexical search to expensive semantic reranking depending on query complexity and budget.
The active learning loop can be extended to transfer knowledge across queries, potentially reducing the per-query labeling cost further by reusing a meta-model.
The framework is directly applicable to retrieval-augmented generation (RAG) pipelines, where it could lower latency and energy consumption by replacing exhaustive LLM reranking with a learned surrogate.
The finding that dense semantic embeddings dominate the feature importance suggests that cheaper embedding models (e.g., MiniLM) can be substituted with only a small loss in accuracy, further reducing computational overhead.
LAAM's reliance on a simple binary disagreement signal opens the door to investigating theoretically grounded acquisition functions (e.g., uncertainty sampling or Bayesian optimization) that might improve sample efficiency or provide guarantees.
The paper's strongest results are on narrative queries; the method shows no benefit over BM25 on short title queries, implying that a hybrid system should dynamically route queries: short ones to lexical retrieval, long ones to the LAAM pipeline. This is acknowledged as future work but left implicit as a design consequence.
The energy comparison relies on a remote API estimate for DeepSeek rather than direct measurement; if local inference hardware becomes more efficient, the relative energy advantage of LAAM may shrink, though the cost savings in API calls would remain.
The greedy disagreement policy is a heuristic; the paper explicitly notes that alternative strategies (e.g., uncertainty sampling) remain unexplored. A principled comparison would clarify whether the observed gains are tied to the specific selection rule or generalise to other active learning approaches.
The TREC Robust 2004 dataset is public and may overlap with LLM training data, making the absolute relevance judgments potentially optimistic. Testing on a private or newer collection would strengthen the claim that the surrogate truly learns reasoning rather than memorized patterns.
Check this review
Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.
How often reviews like this one are right
Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.
How often objections from reviews like this one are right: not yet measured
Reviews by people
This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
Search engines and Large Language Models (LLMs) offer complementary strengths for document retrieval: lexical retrievers which rely on keyword matching are fast and energy-efficient, whereas LLMs capture semantic meaning and excel at interpreting long, context-rich queries. However, this comes at a cost that is computationally and energetically prohibitive. We propose the LLM Active Approximation Model (LAAM), a hybrid retrieval framework that introduces a lightweight learned predictor which serves as an intermediary between semantic retrieval and LLM retrieval. LAAM is refined through an active learning loop where an LLM labels a small number of documents. By concentrating LLM evaluations on the most informative documents, the framework substantially reduces inference cost while preserving retrieval effectiveness. We evaluate the proposed framework on TREC Robust 2004 using Lucene with BM25 retrieval and DeepSeek v3 as the LLM, under three levels of query verbosity. For verbose queries, LAAM achieves 87% of average P@10 achieved by DeepSeek's reranking (0.459 vs. 0.526), while requiring only 3.3% of the per-query energy consumption. LAAM is statistically significantly better than BM25 and is indistinguishable from DeepSeek on average precision, though not on MAP (Friedman test, P<0.05 with post-hoc testing). Overall, our results demonstrate that selectively approximating LLM relevance judgments through active learning enables retrieval accuracy to be controlled directly through the evaluation (and consequently energy) budget. Rather than committing to either inexpensive (and less accurate) lexical retrieval or exhaustive (and expensive) LLM reranking, our framework exposes a continuous spectrum of operating points along the energy–accuracy curve, allowing practitioners to select how to trade retrieval quality with computational budget.
The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-13
The authors' main claim, as the classifier picked it out 0.95
“Overall, our results demonstrate that selectively approximating LLM relevance judgments through active learning enables retrieval accuracy to be controlled directly through the evaluation (and consequently energy) budget.”
How the main claim is stated: asserted 1.00
What the abstract itself states, as probabilities: claims first 0.04 · states limitation 0.60 · human participants 0.03 · controlled comparison 0.94 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.97 · mentions code or data availability 0.03
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| Search engines and Large Language Models (LLMs) offer complementary strengths for document retrieval: lexical retrievers which rely on keyword matching are fast and energy-efficient, whereas LLMs capture semantic meaning and excel at interpreting long, context-rich queries. | background 1.00 | 0.06 | 0.03 | asserted 1.00 |
| However, this comes at a cost that is computationally and energetically prohibitive. | background 0.88 | 0.09 | 0.02 | asserted 0.99 |
| We propose the LLM Active Approximation Model (LAAM), a hybrid retrieval framework that introduces a lightweight learned predictor which serves as an intermediary between semantic retrieval and LLM retrieval. | contribution 0.77 | 0.84 | 0.07 | asserted 1.00 |
| LAAM is refined through an active learning loop where an LLM labels a small number of documents. | method 0.99 | 0.86 | 0.04 | asserted 1.00 |
| By concentrating LLM evaluations on the most informative documents, the framework substantially reduces inference cost while preserving retrieval effectiveness. | result 0.49 | 0.79 | 0.26 | asserted 0.99 |
| We evaluate the proposed framework on TREC Robust 2004 using Lucene with BM25 retrieval and DeepSeek v3 as the LLM, under three levels of query verbosity. | method 0.99 | 0.95 | 0.03 | asserted 0.96 |
| For verbose queries, LAAM achieves 87% of average P@10 achieved by DeepSeek's reranking (0.459 vs. 0.526), while requiring only 3.3% of the per-query energy consumption. | result 1.00 | 0.97 | 0.13 | asserted 1.00 |
| LAAM is statistically significantly better than BM25 and is indistinguishable from DeepSeek on average precision, though not on MAP (Friedman test, P<0.05 with post-hoc testing). | result 1.00 | 0.96 | 0.09 | asserted 1.00 |
| Overall, our results demonstrate that selectively approximating LLM relevance judgments through active learning enables retrieval accuracy to be controlled directly through the evaluation (and consequently energy) budget. | interpretation 0.98 | 0.95 | 0.83 | asserted 1.00 |
| Rather than committing to either inexpensive (and less accurate) lexical retrieval or exhaustive (and expensive) LLM reranking, our framework exposes a continuous spectrum of operating points along the energy--accuracy curve, allowing practitioners to select how to trade retrieval quality with computational budget. | interpretation 0.96 | 0.74 | 0.39 | asserted 1.00 |
What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.98
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 7,821 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Figures (7)
Figures are the authors', reproduced from the paper.
References (44)
- [1] Fu Bang. Gptcache: An open-source semantic cache for llm applications enabling faster answers and cost savings. InProceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023), pages 212–218, 2023 on Pith
- [2] Michael Bendersky and W Bruce Croft. Discovering key concepts in verbose queries. In Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, pages 491–498, 2008 on Pith
- [3] Michael Bendersky and W Bruce Croft. Analysis of long queries in a large scale search log. InProceedings of the 2009 workshop on Web Search Click Data, pages 8–14, 2009 on Pith
- [4] Leo Breiman. Random forests.Machine learning, 45(1):5–32, 2001 on Pith
- [5] Sergey Brin and Lawrence Page. The anatomy of a large-scale hypertextual web search engine.Computer networks and ISDN systems, 30(1-7):107–117, 1998 on Pith
- [6] Kevin Matthe Caramancion.An Interdisciplinary Assessment of the Prophylactic Educa- tional Treatments to Misinformation and Disinformation. State University of New York at Albany, 2022 on Pith
- [7] Kevin Matthe Caramancion. Large language models vs. search engines: Evaluating user preferences across varied information retrieval scenarios.arXiv preprint arXiv:2401.05761, 2024 on PithPith's reviewarXiv
- [8] Ning Cheng, Zhaohui Yan, Ziming Wang, Zhijie Li, Jiaming Yu, Zilong Zheng, Kewei Tu, Jinan Xu, and Wenjuan Han. Potential and limitations of llms in capturing structured semantics: A case study on srl. InInternational Conference on Intelligent Computing, pages 50–61. Springer, 2024 on Pith
- [9] Alex de Vries. The growing energy footprint of artificial intelligence.Joule, 7(10):2191–2194, 2023 on Pith
- [10] Jiazhan Feng, Chongyang Tao, Xiubo Geng, Tao Shen, Can Xu, Guodong Long, Dongyan Zhao, and Daxin Jiang. Synergistic interplay between search and large language models for information retrieval.arXiv preprint arXiv:2305.07402, 2023 on PithPith's reviewarXiv
- [11] Jerome H Friedman. Greedy function approximation: a gradient boosting machine.Annals of statistics, pages 1189–1232, 2001 on Pith
- [12] Joel Gombiner. Carbon footprinting the internet.Consilience, (5):119–124, 2011 on Pith
- [13] Sinan Gultekin, Achille Globo, Andrea Zugarini, Marco Ernandes, and Leonardo Rigutini. An energy-based comparative analysis of common approaches to text classification in the legal domain.arXiv preprint arXiv:2311.01256, 2023 on PithPith's reviewarXiv
- [14] Manish Gupta and Michael Bendersky. Information retrieval with verbose queries. In Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval, pages 1121–1124, 2015 on Pith
- [15] Jerry Huang, Siddarth Madala, Cheng Niu, Julia Hockenmaier, and Tong Zhang. Contextual relevance and adaptive sampling for llm-based document reranking. InProceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 207... on Pith
- [16] Bernard J Jansen, Amanda Spink, and Tefko Saracevic. Real life, real users, and real needs: a study and analysis of user queries on the web.Information processing & management, 36 (2):207–227, 2000 on Pith
- [17] Nidhal Jegham, Marwan Abdelatti, Chan Young Koh, Lassad Elmoubarki, and Abdeltawab Hendawi. How hungry is ai? benchmarking energy, water, and carbon footprint of llm inference.arXiv preprint arXiv:2505.09598, 2025 on PitharXiv
- [18] XiangJi, YesimSungu-Eryilmaz, ElahehMomeni, andRezaRawassizadeh. Speedingupques- tion answering task of language models via inverted index.arXiv preprint arXiv:2210.13578, 2022 on PithPith's reviewarXiv
- [19] Junyoung Kim, Anton Korikov, Jiazhou Liang, Justin Cui, Yifan Simon Liu, Qianfeng Wen, Mark Zhao, and Scott Sanner. Bayesian active learning with gaussian processes guided by llm relevance scoring for dense passage retrieval. InFindings of the Association for Computational Lin... on Pith
- [20] Giridhar Kumaran and Vitor R Carvalho. Reducing long queries using query quality predictors. InProceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, pages 564–571, 2009 on Pith
show 24 more
- [21] Yibin Lei, Yu Cao, Tianyi Zhou, Tao Shen, and Andrew Yates. Corpus-steered query expansion with large language models.arXiv preprint arXiv:2402.18031, 2024 on PithPith's reviewarXiv
- [22] Minghan Li, Éric Gaussier, Juntao Li, and Guodong Zhou. Keyb2: Selecting key blocks is also important for long document ranking with large language models.arXiv preprint arXiv:2411.06254, 2024 on PithPith's reviewarXiv
- [23] Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437, 2024 on PithPith's reviewarXiv
- [24] lucene. Apache lucene.https://lucene.apache.org/ on Pith
- [25] Xueguang Ma, Liang Wang, Nan Yang, Furu Wei, and Jimmy Lin. Fine-tuning llama for multi-stage text retrieval. InProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2421–2425, 2024 on Pith
- [26] Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, and Weizhu Chen. Generation-augmented retrieval for open-domain question answering.arXiv preprint arXiv:2009.08553, 2020 on PithPith's reviewarXiv
- [27] Rodrigo Nogueira, Wei Yang, Jimmy Lin, and Kyunghyun Cho. Document expansion by query prediction.arXiv preprint arXiv:1904.08375, 2019 on PithPith's reviewarXiv
- [28] David Otero and Javier Parapar. Llm-assisted pseudo-relevance feedback. InEuropean Conference on Information Retrieval, pages 452–459. Springer, 2026 on Pith
- [29] Ripal Ranpara and CK Kumbharana. Contextual information retrieval search engine challenges. InRising Threats in Expert Applications and Solutions: Proceedings of FICR- TEAS 2020, pages 269–273. Springer, 2021 on Pith
- [30] Stephen E Robertson and Steve Walker. Some simple effective approximations to the 2-poisson model for probabilistic weighted retrieval. InSIGIR’94: Proceedings of the Seventeenth Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, or... on Pith
- [31] Gerard Salton and Christopher Buckley. Term-weighting approaches in automatic text retrieval.Information Processing & Management, 24(5), 1988. doi: https://doi.org/10. 1016/0306-4573(88)90021-0. URL https://www.sciencedirect.com/science/article/ pii/0306457388900210 on Pith
- [32] Gerard Salton, Anita Wong, and Chung-Shu Yang. A vector space model for automatic indexing.Communications of the ACM, 18(11):613–620, 1975 on Pith
- [33] Claude Sammut and Geoffrey I Webb.Encyclopedia of machine learning. Springer Science & Business Media, 2011 on Pith
- [34] Harrisen Scells, Shengyao Zhuang, and Guido Zuccon. Reduce, reuse, recycle: Green information retrieval research. InProceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2825–2837, 2022 on Pith
- [35] Craig Silverstein, Hannes Marais, Monika Henzinger, and Michael Moricz. Analysis of a very large web search engine query log. InAcm sigir forum, volume 33, pages 6–12. ACM New York, NY, USA, 1999 on Pith
- [36] Weiwei Sun, Lingyong Yan, Xinyu Ma, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, and Zhaochun Ren. Is chatgpt good at search? investigating large language models as re-ranking agents. InProceedings of the 2023 conference on empirical methods in natural language proces... on Pith
- [37] Ellen M Voorhees. Overview of the trec 2004 robust track. InTREC, volume 4, 2004 on Pith
- [38] Liang Wang, Nan Yang, and Furu Wei. Query2doc: Query expansion with large language models.arXiv preprint arXiv:2303.07678, 2023 on PithPith's reviewarXiv
- [39] Orion Weller, Benjamin Chang, Sean MacAvaney, Kyle Lo, Arman Cohan, Benjamin Van Durme, Dawn Lawrie, and Luca Soldaini. Followir: Evaluating and teaching information retrieval models to follow instructions. InProceedings of the 2025 Conference of the Nations of the Americas Ch... on Pith
- [40] Ruixuan Xiao, Yiwen Dong, Junbo Zhao, Runze Wu, Minmin Lin, Gang Chen, and Haobo Wang. Freeal: Towards human-free active learning in the era of large language models. arXiv preprint arXiv:2311.15614, 2023 on PithPith's reviewarXiv
- [41] Haoyi Xiong, Jiang Bian, Yuchen Li, Xuhong Li, Mengnan Du, Shuaiqiang Wang, Dawei Yin, and Sumi Helal. When search engine services meet large language models: visions and challenges.IEEE Transactions on Services Computing, 2024 on Pith
- [42] Xueliang Yan, Guanglai Gao, Xiangdong Su, Hongxi Wei, Xueliang Zhang, and Qianqian Lu. Hidden markov model for term weighting in verbose queries. InInformation Access Evalua- tion. Multilinguality, Multimodality, and Visual Analytics: Third International Conference of the CLEF... on Pith
- [43] Ruoyu Zhang, Yanzeng Li, Yongliang Ma, Ming Zhou, and Lei Zou. Llmaaa: Making large language models as active annotators.arXiv preprint arXiv:2310.19596, 2023 on PithPith's reviewarXiv
- [44] Yutao Zhu, Huaying Yuan, Shuting Wang, Jiongnan Liu, Wenhan Liu, Chenlong Deng, Haonan Chen, Zheng Liu, Zhicheng Dou, and Ji-Rong Wen. Large language models for information retrieval: A survey.arXiv preprint arXiv:2308.07107, 2023. 20 A LLM Prompt The following prompt was used... on PitharXiv
Challenges and discussion
Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment