Pith. sign in

REVIEW 20 cited by

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

Not yet reviewed by Pith; the record is open.

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

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2212.10375 v2 pith:756H32HF submitted 2022-12-20 cs.CL cs.AI

Zhiyong Wu , Yaoxiang Wang , Jiacheng Ye , Lingpeng Kong This is my paper · ORCID
classification cs.CLcs.AI
keywords in-contextself-adaptivelearningselectionalgorithmscommonexampleordering
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Despite the surprising few-shot performance of in-context learning (ICL), it is still a common practice to randomly sample examples to serve as context. This paper advocates a new principle for ICL: self-adaptive in-context learning. The self-adaption mechanism is introduced to help each sample find an in-context example permutation (i.e., selection and ordering) that can derive the correct prediction, thus maximizing performance. To validate the effectiveness of self-adaptive ICL, we propose a general select-then-rank framework and instantiate it with new selection and ranking algorithms. Upon extensive evaluation on eight different NLP datasets, our self-adaptive ICL method achieves a 40% relative improvement over the common practice setting. Further analysis reveals the enormous potential of self-adaptive ICL that it might be able to close the gap between ICL and finetuning given more advanced algorithms. Our code is released to facilitate future research in this area: https://github.com/Shark-NLP/self-adaptive-ICL

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 20 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling

    cs.AI 2026-08 conditional novelty 6.0 of 10

    Per-step retrieval of solved exemplars injected into the reasoning trace improves test-time scaling accuracy, with up to 13.4 absolute points gained on AIME 2025.

  2. Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention

    cs.CL 2025-09 conditional novelty 6.0 of 10

    ICR extracts shared attention directions from in-context learning and routes them at inference time, enabling zero-shot reuse across tasks.

  3. KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning

    cs.LG 2025-09 reject novelty 6.0 of 10

    KITE greedily selects in-context examples by maximizing a kernelized query-specific relevance score plus a D-optimal design diversity term, and reports accuracy gains over KATE, BM25, and DPP baselines on five classif...

  4. STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment

    cs.CL 2025-08 conditional novelty 6.0 of 10

    A structure-aware exemplar retriever with a hidden-state syntactic injection module improves in-context semantic parsing across four benchmarks.

  5. Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples

    cs.CL 2025-06 reject novelty 6.0 of 10

    Training a retriever with a reward-model-scored pairwise ranking loss improves reward model accuracy on low-resource Indic languages in the paper's evaluation, though that evaluation is biased.

  6. SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis

    cs.SE 2025-05 conditional novelty 6.0 of 10

    Large language models perform poorly on a new C-code vulnerability benchmark, indicating they rely on pattern matching rather than genuine reasoning.

  7. Rethinking Invariance in In-context Learning

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A leave-one-out attention preprocessing scheme makes in-context learning permutation invariant without sacrificing access to other context examples, improving length and out-of-distribution generalization.

  8. OptiSeq: Ordering Examples On-The-Fly for In-Context Learning

    cs.LG 2025-01 conditional novelty 6.0 of 10

    OptiSeq selects the in-context example ordering whose output gets the highest zero-shot log-likelihood, improving few-shot accuracy by up to 10.5 points in tests on API sequencing and classification.

  9. PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks

    cs.CL 2024-12 conditional novelty 6.0 of 10

    PromptRefine uses alternating minimization over language-specific retrievers plus diversity-aware DPP fine-tuning to select cross-lingual in-context examples, improving few-shot generation in low-resource Indic languages.

  10. DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer

    cs.AI 2025-07 conditional novelty 5.0 of 10

    DICE dynamically retrieves the most relevant in-context demonstrations at each agent step, and in this preprint it raises exact-match and success-rate scores on HotpotQA, ALFWorld, and Webshop across ReAct, Reflexion,...

  11. Unveiling Effective In-Context Configurations for Image Captioning: An External & Internal Analysis

    cs.CL 2025-07 conditional novelty 5.0 of 10

    For Flamingo-style models, increasing the number of in-context examples improves language coherence but degrades visual-text alignment, and similarity-based image retrieval inflates CIDEr scores by encouraging caption...

  12. How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models?

    cs.CL 2025-06 conditional novelty 5.0 of 10

    Retrieving a semantically similar example and voting over paraphrased versions of it improves conversational emotion recognition macro F1 over random in-context examples.

  13. A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences

    cs.CL 2025-06 reject novelty 5.0 of 10

    A multi-agent GPT-4O pipeline with an internal semantic-lexical gate claims 70% success on simplifying 100 video game sentences, versus 48% for a single-agent version.

  14. Mimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language Models

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Vision-language models improve little, often not at all, when given demonstrations, even when demonstrations contain explicit reasoning steps.

  15. Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale

    cs.CL 2025-05 conditional novelty 5.0 of 10

    FGO is a divide-and-conquer framework that runs LLM-based agent optimization on dataset subsets and recursively merges the optimized prompts or tool sets into a final agent system.

  16. E-InMeMo: Enhanced Prompting for Visual In-Context Learning

    cs.CV 2025-04 conditional novelty 5.0 of 10

    Adding a learnable pixel-level perturbation to the in-context pair improves MAE-VQGAN visual in-context learning on segmentation and object detection benchmarks.

  17. Don't Just Demo, Teach Me the Principles: A Principle-Based Multi-Agent Prompting Strategy for Text Classification

    cs.CL 2025-02 conditional novelty 5.0 of 10

    A principle-based multi-agent prompting strategy improves zero-shot LLM text classification by generating task-level principles from a few demonstrations and reusing them for all test instances.

  18. StaICC: Standardized Evaluation for Classification Task in In-context Learning

    cs.CL 2025-01 conditional novelty 5.0 of 10

    StaICC standardizes in-context classification evaluation with fixed prompts and splits, then measures 29 LMs and 10 inference methods under those fixed settings.

  19. Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models

    cs.AI 2025-04 conditional novelty 4.0 of 10

    A structured survey of reinforcement-learning-based reasoning methods for multimodal large language models, including a taxonomy, reward design review, benchmark tables, and open challenges.

  20. Memory-Augmented Agent Training for Business Document Understanding

    cs.CL 2024-12 conditional novelty 4.0 of 10

    Matrix iteratively refines an LLM agent's memory from training trajectories and outperforms prompting and vanilla agent baselines on private UBL invoice transport-reference extraction, though gains on the released ano...

Pith tools