Pith. sign in

REVIEW 2 major objections 2 minor 48 references

Reranking few-shot examples can degrade performance, but uncertainty-based gating prevents the harm.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-07-02 19:54 UTC pith:GUX4FFXT

load-bearing objection Reranking can hurt few-shot performance on some instances, and the uncertainty gate lets you skip it selectively for cost savings, but the paper needs to show that uncertainty actually tracks the reranking delta. the 2 major comments →

arxiv 2606.31087 v2 pith:GUX4FFXT submitted 2026-06-30 cs.CL cs.AI

When Reranking Hurts: Uncertainty-Based Gating for Few-Shot Reranking

Orian Dabod , Amir DN Cohen , Gabriel Stanovsky This is my paper
classification cs.CL cs.AI
keywords few-shot learningrerankinguncertainty estimationlarge language modelsnatural language understandingmachine translationgated selection
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper challenges the common assumption in few-shot learning that reranking always retrieved examples will improve results. It shows that this step can actually lower performance in some cases. To address this, the authors introduce Training-Free Gated Reranking, a method that uses the language model's own uncertainty to decide on each instance whether reranking is worth doing. Experiments on many models and tasks show this saves significant computation and can raise average accuracy. Readers should care because it reveals that blindly adding more steps does not always lead to better outcomes in prompting LLMs.

Core claim

Few-shot selection typically assumes that reranking retrieved examples always improves performance. We challenge this view by identifying that the expensive reranking step can in fact degrade performance. Instead, we propose Training-Free Gated Reranking, which decides whether to rerank the few-shot examples based on the model's uncertainty. Extensive experiments across 8 LLMs, covering 7 NLU datasets and 9 MT domain-language combinations, demonstrate that our approach reduces computational costs by 15%-80% while improving average performance by up to 2%.

What carries the argument

Training-Free Gated Reranking, a decision mechanism that uses the model's uncertainty to determine whether to apply reranking to few-shot examples on a per-instance basis.

Load-bearing premise

The model's uncertainty serves as a reliable indicator of whether reranking will help or hurt performance for a specific input.

What would settle it

An experiment that measures accuracy on low-uncertainty instances both with and without reranking to test whether skipping reranking produces higher accuracy than applying it.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Reranking should only be performed on high-uncertainty instances.
  • This selective approach reduces computational costs by 15% to 80%.
  • Average performance improves by up to 2% across tested models and datasets.
  • Reranking is most beneficial when targeted at high-uncertainty instances.
  • Higher computational cost does not guarantee better performance.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same uncertainty signal might help decide when to use other costly inference techniques like chain-of-thought.
  • Different ways to measure uncertainty could be tested to see if they improve the gating decision.
  • This finding questions the value of always using more sophisticated retrieval methods without checking their impact per instance.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

2 major / 2 minor

Summary. The paper challenges the common assumption in few-shot in-context learning that reranking retrieved examples always improves performance. It identifies cases where reranking degrades results and proposes Training-Free Gated Reranking, a method that uses the base model's uncertainty to decide per-instance whether to apply the reranking step. Experiments across 8 LLMs, 7 NLU datasets, and 9 MT settings report 15-80% compute savings and up to 2% average performance gains, concluding that reranking should be applied selectively to high-uncertainty instances.

Significance. If the uncertainty signal reliably predicts per-instance reranking benefit, the approach offers a practical, training-free way to reduce the cost of few-shot reranking while improving results. This would be a useful empirical contribution to efficient prompting methods, particularly if accompanied by reproducible code or clear per-instance diagnostics.

major comments (2)
  1. [Abstract / method description] The central claim requires that model uncertainty correlates with the sign of the reranking performance delta on individual instances (i.e., high-uncertainty cases are precisely those where reranking helps). The abstract and method description provide no per-instance correlation statistics, scatter plots, or ablation against random gating at matched compute budget; without this evidence the gating mechanism reduces to an arbitrary filter and the reported gains could be explained by any selective mechanism.
  2. [Experiments section] The experimental results are reported only as averages across models and datasets. No breakdown by uncertainty quartile, no statistical significance tests on the gated vs. always-rerank comparison, and no error analysis on cases where gating errs are mentioned, leaving the load-bearing assumption unverified even if aggregate numbers improve.
minor comments (2)
  1. [Method] Clarify the exact uncertainty measure (e.g., entropy over what distribution, token-level or sequence-level) and how the gating threshold is chosen without any training or validation data.
  2. [Method] The claim of 'training-free' should be reconciled with any hyper-parameters that control the uncertainty threshold or the number of reranked candidates.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address the major comments point by point below and will incorporate revisions to strengthen the presentation of per-instance evidence.

read point-by-point responses

  1. Referee: [Abstract / method description] The central claim requires that model uncertainty correlates with the sign of the reranking performance delta on individual instances (i.e., high-uncertainty cases are precisely those where reranking helps). The abstract and method description provide no per-instance correlation statistics, scatter plots, or ablation against random gating at matched compute budget; without this evidence the gating mechanism reduces to an arbitrary filter and the reported gains could be explained by any selective mechanism.

    Authors: We agree that explicit per-instance validation is necessary to support the central claim. The experiments section contains correlation analysis between uncertainty scores and reranking deltas along with supporting visualizations, but these are not referenced in the abstract or method description. We will revise the abstract and method sections to point to this analysis and add a new ablation comparing the uncertainty-based gate against random selection at equivalent compute budgets. revision: yes

  2. Referee: [Experiments section] The experimental results are reported only as averages across models and datasets. No breakdown by uncertainty quartile, no statistical significance tests on the gated vs. always-rerank comparison, and no error analysis on cases where gating errs are mentioned, leaving the load-bearing assumption unverified even if aggregate numbers improve.

    Authors: We acknowledge that the current presentation relies primarily on aggregate metrics. We will add per-quartile performance breakdowns, statistical significance tests for the gated versus always-rerank conditions, and a dedicated error analysis of gating mistakes in the revised experiments section. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical method with no derivations or self-referential fits

full rationale

The paper proposes Training-Free Gated Reranking as an empirical heuristic that gates reranking based on model uncertainty, validated through experiments on 8 LLMs, 7 NLU datasets, and 9 MT combinations. No equations, parameter fits, or derivation chains appear in the abstract or described approach. The method is explicitly training-free, and performance claims rest on direct experimental averages rather than any reduction of outputs to inputs by construction, self-citation load-bearing premises, or renamed known results. The uncertainty signal is presented as an observed pattern from experiments, not a fitted or self-defined quantity.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Review is based on abstract only; the paper explicitly challenges the domain assumption that reranking always helps but provides no further parameters or entities.

axioms (1)
  • domain assumption Reranking retrieved examples always improves performance in few-shot selection
    The abstract states that few-shot selection typically assumes this and then challenges it with the gated approach.

pith-pipeline@v0.9.1-grok · 5648 in / 1266 out tokens · 38962 ms · 2026-07-02T19:54:10.954115+00:00 · methodology

0 comments
read the original abstract

Few-shot selection typically assumes that reranking retrieved examples always improves performance. We challenge this view by identifying that the expensive reranking step can in fact degrade performance. Instead, we propose \emph{Training-Free Gated Reranking}, which decides whether to rerank the few-shot examples based on the model's uncertainty. Extensive experiments across 8 LLMs, covering 7 NLU datasets and 9 MT domain-language combinations, demonstrate that our approach reduces computational costs by 15\%-80\% while improving average performance by up to 2\%. These findings indicate that higher computational cost does not guarantee better performance, and that reranking is most beneficial when targeted at high-uncertainty instances.

Figures

Figures reproduced from arXiv: 2606.31087 by Amir DN Cohen, Gabriel Stanovsky, Orian Dabod.

Figure 1
Figure 1. Figure 1: Relative performance impact versus computational [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

48 extracted references · 12 canonical work pages · 1 internal anchor

  1. [1]

    and Way, Andy , booktitle =

    Moslem, Yasmin and Haque, Rejwanul and Kelleher, John D. and Way, Andy , booktitle =. Adaptive Machine Translation with Large Language Models , url =

  2. [2]

    Nearest Neighbor Machine Translation , url =

    Urvashi Khandelwal and Angela Fan and Dan Jurafsky and Luke Zettlemoyer and Mike Lewis , bibsource =. Nearest Neighbor Machine Translation , url =. 9th International Conference on Learning Representations,

  3. [3]

    Neural Machine Translation with Monolingual Translation Memory , url =

    Cai, Deng and Wang, Yan and Li, Huayang and Lam, Wai and Liu, Lemao , booktitle =. Neural Machine Translation with Monolingual Translation Memory , url =. doi:10.18653/v1/2021.acl-long.567 , editor =

    work page doi:10.18653/v1/2021.acl-long.567 2021

  4. [4]

    Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles , url =

    Tan, Weiting and Xu, Haoran and Shen, Lingfeng and Li, Shuyue Stella and Murray, Kenton and Koehn, Philipp and Van Durme, Benjamin and Chen, Yunmo , booktitle =. Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles , url =

  5. [5]

    RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs , url =

    Yue Yu and Wei Ping and Zihan Liu and Boxin Wang and Jiaxuan You and Chao Zhang and Mohammad Shoeybi and Bryan Catanzaro , bibsource =. RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs , url =. Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, V...

    2024

  6. [6]

    Adaptive-

    Jeong, Soyeong and Baek, Jinheon and Cho, Sukmin and Hwang, Sung Ju and Park, Jong , booktitle =. Adaptive-

  7. [7]

    TARG: Training-Free Adaptive Retrieval Gating for Efficient RAG , url =

    Yufeng Wang and Lu wei and Haibin Ling , journal =. TARG: Training-Free Adaptive Retrieval Gating for Efficient RAG , url =

  8. [8]

    Dynamic and Parametric Retrieval-Augmented Generation , url =

    Weihang Su and Qingyao Ai and Jingtao Zhan and Qian Dong and Yiqun Liu , journal =. Dynamic and Parametric Retrieval-Augmented Generation , url =

  9. [9]

    Revisiting Demonstration Selection Strategies in In-Context Learning , url =

    Keqin Peng and Liang Ding and Yancheng Yuan and Xuebo Liu and Min Zhang and Yuanxin Ouyang and Dacheng Tao , journal =. Revisiting Demonstration Selection Strategies in In-Context Learning , url =

  10. [10]

    Andrey Malinin and Mark J. F. Gales , bibsource =. Uncertainty Estimation in Autoregressive Structured Prediction , url =. 9th International Conference on Learning Representations,

  11. [11]

    Weinberger , bibsource =

    Chuan Guo and Geoff Pleiss and Yu Sun and Kilian Q. Weinberger , bibsource =. On Calibration of Modern Neural Networks , url =. Proceedings of the 34th International Conference on Machine Learning,

  12. [12]

    Witbrock, Michael and Padriac Amato Tahua O

    Pistotti, Timothy and J. Witbrock, Michael and Padriac Amato Tahua O. The Benefits of Being Uncertain: Perplexity as a Signal for Naturalness in Multilingual Machine Translation , url =. Proceedings of the 2nd Workshop on Uncertainty-Aware NLP (UncertaiNLP 2025) , doi =

    2025

  13. [13]

    Revisiting Logit Distributions for Reliable Out-of-Distribution Detection , url =

    Jiachen Liang and Ruibing Hou and Minyang Hu and Hong Chang and Shiguang Shan and Xilin Chen , journal =. Revisiting Logit Distributions for Reliable Out-of-Distribution Detection , url =

  14. [14]

    Aaron Grattafiori and Abhimanyu Dubey and Abhinav Jauhri and Abhinav Pandey and Abhishek Kadian and Ahmad Al-Dahle and Aiesha Letman and Akhil Mathur and Alan Schelten and Alex Vaughan and Amy Yang and Angela Fan and Anirudh Goyal and Anthony Hartshorn and Aobo Yang and Archi Mitra and Archie Sravankumar and Artem Korenev and Arthur Hinsvark and Arun Rao ...

  15. [15]

    Qwen2.5 Technical Report , url =

    Qwen and : and An Yang and Baosong Yang and Beichen Zhang and Binyuan Hui and Bo Zheng and Bowen Yu and Chengyuan Li and Dayiheng Liu and Fei Huang and Haoran Wei and Huan Lin and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Yang and Jiaxi Yang and Jingren Zhou and Junyang Lin and Kai Dang and Keming Lu and Keqin Bao and Kexin Yang and Le Yu an...

  16. [16]

    Qwen3 Technical Report , url =

    An Yang and Anfeng Li and Baosong Yang and Beichen Zhang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Gao and Chengen Huang and Chenxu Lv and Chujie Zheng and Dayiheng Liu and Fan Zhou and Fei Huang and Feng Hu and Hao Ge and Haoran Wei and Huan Lin and Jialong Tang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Yang and Jiaxi Yang and...

  17. [17]

    Albert Q. Jiang and Alexandre Sablayrolles and Arthur Mensch and Chris Bamford and Devendra Singh Chaplot and Diego de las Casas and Florian Bressand and Gianna Lengyel and Guillaume Lample and Lucile Saulnier and Lélio Renard Lavaud and Marie-Anne Lachaux and Pierre Stock and Teven Le Scao and Thibaut Lavril and Thomas Wang and Timothée Lacroix and Willi...

  18. [18]

    Shivalika Singh and Freddie Vargus and Daniel Dsouza and Börje F. Karlsson and Abinaya Mahendiran and Wei-Yin Ko and Herumb Shandilya and Jay Patel and Deividas Mataciunas and Laura OMahony and Mike Zhang and Ramith Hettiarachchi and Joseph Wilson and Marina Machado and Luisa Souza Moura and Dominik Krzemiński and Hakimeh Fadaei and Irem Ergün and Ifeoma ...

  19. [19]

    Parallel Data, Tools and Interfaces in

    Tiedemann, J. Parallel Data, Tools and Interfaces in. Proceedings of the Eighth International Conference on Language Resources and Evaluation (

  20. [20]

    Steinberger, Ralf and Pouliquen, Bruno and Widiger, Anna and Ignat, Camelia and Erjavec, Toma. The. Proceedings of the Fifth International Conference on Language Resources and Evaluation (

  21. [21]

    Jan Melechovsky, Abhinaba Roy, and Dorien Herremans

    Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, Wei-Jing , booktitle =. doi:10.3115/1073083.1073135 , editor =

    work page doi:10.3115/1073083.1073135

  22. [22]

    and Zerva, Chrysoula and Farinha, Ana C and Maroti, Christine and C

    Rei, Ricardo and Treviso, Marcos and Guerreiro, Nuno M. and Zerva, Chrysoula and Farinha, Ana C and Maroti, Christine and C. de Souza, Jos. Proceedings of the Seventh Conference on Machine Translation (WMT) , editor =

  23. [23]

    Popovi. chr. Proceedings of the Tenth Workshop on Statistical Machine Translation , doi =

  24. [24]

    Text Embeddings by Weakly-Supervised Contrastive Pre-training , url =

    Liang Wang and Nan Yang and Xiaolong Huang and Binxing Jiao and Linjun Yang and Daxin Jiang and Rangan Majumder and Furu Wei , journal =. Text Embeddings by Weakly-Supervised Contrastive Pre-training , url =

  25. [25]

    Robertson and Hugo Zaragoza , journal =

    Stephen E. Robertson and Hugo Zaragoza , journal =. The Probabilistic Relevance Framework: BM25 and Beyond , url =

  26. [26]

    Six Challenges for Neural Machine Translation , url =

    Koehn, Philipp and Knowles, Rebecca , booktitle =. Six Challenges for Neural Machine Translation , url =. doi:10.18653/v1/W17-3204 , editor =

    work page doi:10.18653/v1/w17-3204

  27. [27]

    Multilingual E5 Text Embeddings: A Technical Report , url =

    Liang Wang and Nan Yang and Xiaolong Huang and Linjun Yang and Rangan Majumder and Furu Wei , journal =. Multilingual E5 Text Embeddings: A Technical Report , url =

  28. [28]

    In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation , url =

    Zebaze, Armel Randy and Sagot, Beno. In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation , url =. Findings of the Association for Computational Linguistics: NAACL 2025 , doi =

    2025

  29. [29]

    Efficiently Scaling Transformer Inference , url =

    Reiner Pope and Sholto Douglas and Aakanksha Chowdhery and Jacob Devlin and James Bradbury and Anselm Levskaya and Jonathan Heek and Kefan Xiao and Shivani Agrawal and Jeff Dean , journal =. Efficiently Scaling Transformer Inference , url =

  30. [30]

    Chitale and Jay Gala and Raj Dabre , journal =

    Pranjal A. Chitale and Jay Gala and Raj Dabre , journal =. An Empirical Study of In-context Learning in LLMs for Machine Translation , url =

  31. [31]

    Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine , url =

    Wenxiang Jiao and Wenxuan Wang and Jen-tse Huang and Xing Wang and Shuming Shi and Zhaopeng Tu , journal =. Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine , url =

  32. [32]

    Tom B. Brown and Benjamin Mann and Nick Ryder and Melanie Subbiah and Jared Kaplan and Prafulla Dhariwal and Arvind Neelakantan and Pranav Shyam and Girish Sastry and Amanda Askell and Sandhini Agarwal and Ariel Herbert. Language Models are Few-Shot Learners , url =. Advances in Neural Information Processing Systems 33: Annual Conference on Neural Informa...

    2020

  33. [33]

    Prompting

    Vilar, David and Freitag, Markus and Cherry, Colin and Luo, Jiaming and Ratnakar, Viresh and Foster, George , booktitle =. Prompting. doi:10.18653/v1/2023.acl-long.859 , editor =

    work page doi:10.18653/v1/2023.acl-long.859 2023

  34. [34]

    Prompting Large Language Model for Machine Translation:

    Biao Zhang and Barry Haddow and Alexandra Birch , bibsource =. Prompting Large Language Model for Machine Translation:. International Conference on Machine Learning,

  35. [35]

    In-context Examples Selection for Machine Translation , url =

    Agrawal, Sweta and Zhou, Chunting and Lewis, Mike and Zettlemoyer, Luke and Ghazvininejad, Marjan , booktitle =. In-context Examples Selection for Machine Translation , url =. doi:10.18653/v1/2023.findings-acl.564 , editor =

    work page doi:10.18653/v1/2023.findings-acl.564 2023

  36. [36]

    What Makes Good In-Context Examples for

    Liu, Jiachang and Shen, Dinghan and Zhang, Yizhe and Dolan, Bill and Carin, Lawrence and Chen, Weizhu , booktitle =. What Makes Good In-Context Examples for. doi:10.18653/v1/2022.deelio-1.10 , editor =

    work page doi:10.18653/v1/2022.deelio-1.10 2022

  37. [37]

    Adaptive Few-shot Prompting for Machine Translation with Pre-trained Language Models , url =

    Lei Tang and Jinghui Qin and Wenxuan Ye and Hao Tan and Zhijing Yang , journal =. Adaptive Few-shot Prompting for Machine Translation with Pre-trained Language Models , url =

  38. [38]

    Improving Passage Retrieval with Zero-Shot Question Generation , url =

    Sachan, Devendra and Lewis, Mike and Joshi, Mandar and Aghajanyan, Armen and Yih, Wen-tau and Pineau, Joelle and Zettlemoyer, Luke , booktitle =. Improving Passage Retrieval with Zero-Shot Question Generation , url =. doi:10.18653/v1/2022.emnlp-main.249 , editor =

    work page doi:10.18653/v1/2022.emnlp-main.249 2022

  39. [39]

    Brown and Benjamin Chess and Rewon Child and Scott Gray and Alec Radford and Jeffrey Wu and Dario Amodei , journal =

    Jared Kaplan and Sam McCandlish and Tom Henighan and Tom B. Brown and Benjamin Chess and Rewon Child and Scott Gray and Alec Radford and Jeffrey Wu and Dario Amodei , journal =. Scaling Laws for Neural Language Models , url =

  40. [40]

    Learning to Retrieve In-Context Examples for Large Language Models , url =

    Wang, Liang and Yang, Nan and Wei, Furu , booktitle =. Learning to Retrieve In-Context Examples for Large Language Models , url =

  41. [41]

    Unified Demonstration Retriever for In-Context Learning , url =

    Li, Xiaonan and Lv, Kai and Yan, Hang and Lin, Tianyang and Zhu, Wei and Ni, Yuan and Xie, Guotong and Wang, Xiaoling and Qiu, Xipeng , booktitle =. Unified Demonstration Retriever for In-Context Learning , url =. doi:10.18653/v1/2023.acl-long.256 , editor =

    work page doi:10.18653/v1/2023.acl-long.256 2023

  42. [42]

    Demystifying Prompts in Language Models via Perplexity Estimation , url =

    Gonen, Hila and Iyer, Srini and Blevins, Terra and Smith, Noah and Zettlemoyer, Luke , booktitle =. Demystifying Prompts in Language Models via Perplexity Estimation , url =. doi:10.18653/v1/2023.findings-emnlp.679 , editor =

    work page doi:10.18653/v1/2023.findings-emnlp.679 2023

  43. [43]

    and Ng, Andrew and Potts, Christopher , booktitle =

    Socher, Richard and Perelygin, Alex and Wu, Jean and Chuang, Jason and Manning, Christopher D. and Ng, Andrew and Potts, Christopher , booktitle =. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , url =

  44. [44]

    Bowman , bibsource =

    Alex Wang and Amanpreet Singh and Julian Michael and Felix Hill and Omer Levy and Samuel R. Bowman , bibsource =. 7th International Conference on Learning Representations,

  45. [45]

    A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference

    Williams, Adina and Nangia, Nikita and Bowman, Samuel , booktitle =. A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference , url =. doi:10.18653/v1/N18-1101 , editor =

    work page internal anchor Pith review doi:10.18653/v1/n18-1101

  46. [46]

    M\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity , url =

    Tyler Griggs and Xiaoxuan Liu and Jiaxiang Yu and Doyoung Kim and Wei-Lin Chiang and Alvin Cheung and Ion Stoica , journal =. M\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity , url =

  47. [47]

    Learning To Retrieve Prompts for In-Context Learning , url =

    Rubin, Ohad and Herzig, Jonathan and Berant, Jonathan , booktitle =. Learning To Retrieve Prompts for In-Context Learning , url =. doi:10.18653/v1/2022.naacl-main.191 , editor =

    work page doi:10.18653/v1/2022.naacl-main.191 2022

  48. [48]

    Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering , url =

    Wu, Zhiyong and Wang, Yaoxiang and Ye, Jiacheng and Kong, Lingpeng , booktitle =. Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering , url =. doi:10.18653/v1/2023.acl-long.79 , editor =

    work page doi:10.18653/v1/2023.acl-long.79 2023