mlsanityData to 14 Oct 2026

Exploring Explanations Improves the Robustness of In-Context Learning

arXiv 2506.02378 ↗First posted 3 Jun 2025cs.CL cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

In-context learning (ICL) has emerged as a successful paradigm for leveraging large language models (LLMs). However, it often struggles to generalize beyond the distribution of the provided demonstrations. A recent advancement in enhancing robustness is ICL with explanations (X-ICL), which improves prediction reliability by guiding LLMs to understand and articulate the reasoning behind correct labels. Building on this approach, we introduce an advanced framework that extends X-ICL by systematically exploring explanations for all possible labels (X2-ICL), thereby enabling more comprehensive and robust decision-making. Experimental results on multiple natural language understanding datasets validate the effectiveness of X2-ICL, demonstrating significantly improved robustness to out-of-distribution data compared to the existing ICL approaches.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 36 of its 55 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

36 of 55 references.

References · 36

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2019Invariant Risk Minimizationcited by 1,854
  6. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  7. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  8. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  9. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 876
  10. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 807
  11. 2023Whose Opinions Do Language Models Reflect?cited by 773
  12. 2018Annotation Artifacts in Natural Language Inference Datacited by 671
24 more
  1. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 523
  2. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 402
  3. 2020Environment Inference for Invariant Learningcited by 306
  4. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 280
  5. 2018Stress Test Evaluation for Natural Language Inferencecited by 213
  6. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 211
  7. 2019Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasetscited by 175
  8. 2020What Can We Learn from Collective Human Opinions on Natural Language Inference Data?cited by 153
  9. 2023Compositional Exemplars for In-context Learningcited by 144
  10. 2022Diverse Demonstrations Improve In-context Compositional Generalizationcited by 139
  11. 2019End-to-End Bias Mitigation by Modelling Biases in Corporacited by 128
  12. 2023Change is Hard: A Closer Look at Subpopulation Shiftcited by 120
  13. 2019Unlearn Dataset Bias in Natural Language Inference by Fitting the Residualcited by 119
  14. 2023Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learningcited by 69
  15. 2023Coverage-based Example Selection for In-Context Learningcited by 59
  16. 2023Explore Spurious Correlations at the Concept Level in Language Models for Text Classificationcited by 48
  17. 2024Examining the robustness of LLM evaluation to the distributional assumptions of benchmarkscited by 31
  18. 2022Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negationcited by 25
  19. 2023Explanation-based Finetuning Makes Models More Robust to Spurious Cuescited by 25
  20. 2023In-context Learning Generalizes, But Not Always Robustly: The Case of Syntaxcited by 22
  21. 2023Robust Prompt Optimization for Large Language Models Against Distribution Shiftscited by 19
  22. 2020HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inferencecited by 17
  23. 2020An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inferencecited by 16
  24. 2024Rectifying Demonstration Shortcut in In-Context Learningcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptationcited by 0
  2. 2026Cross-Model Humor Preference Modeling with Cards Against Humanitycited by 0