Looped linear transformers with LN provably converge via GD to implement the power method on principal component prediction.
hub Canonical reference
A Survey on In-context Learning
Canonical reference. 93% of citing Pith papers cite this work as background.
80
Pith papers citing it
Background
93% of classified citations
abstract
With the increasing capabilities of large language models (LLMs), in-context learning (ICL) has emerged as a new paradigm for natural language processing (NLP), where LLMs make predictions based on contexts augmented with a few examples. It has been a significant trend to explore ICL to evaluate and extrapolate the ability of LLMs. In this paper, we aim to survey and summarize the progress and challenges of ICL. We first present a formal definition of ICL and clarify its correlation to related studies. Then, we organize and discuss advanced techniques, including training strategies, prompt designing strategies, and related analysis. Additionally, we explore various ICL application scenarios, such as data engineering and knowledge updating. Finally, we address the challenges of ICL and suggest potential directions for further research. We hope that our work can encourage more research on uncovering how ICL works and improving ICL.
hub tools
citation-role summary
background 29
method 1
citation-polarity summary
claims ledger
- abstract With the increasing capabilities of large language models (LLMs), in-context learning (ICL) has emerged as a new paradigm for natural language processing (NLP), where LLMs make predictions based on contexts augmented with a few examples. It has been a significant trend to explore ICL to evaluate and extrapolate the ability of LLMs. In this paper, we aim to survey and summarize the progress and challenges of ICL. We first present a formal definition of ICL and clarify its correlation to related studies. Then, we organize and discuss advanced techniques, including training strategies, prompt des
co-cited works
representative citing papers
NLI autonomously discovers a vocabulary of primitive operations and interprets variable-length programs via a neural executor, allowing end-to-end training and gradient-based test-time adaptation that outperforms prior methods on combinatorial generalization tasks.
DICE formalizes multi-agent LLM coordination as discounted incomplete-information Markov games and introduces Heterogeneous Quantal Response Equilibrium (HQRE) to achieve unique stable equilibria with bounded regret, demonstrated via prompt-control and fine-tuning algorithms on eleven benchmarks.
VASO is a verification-guided self-evolution framework for LLM robot skill contracts that reaches 97.2% formal-specification compliance on Jackal and quadcopter tasks using under 100 samples.
WALDO reformulates zero-shot anomaly localisation as comparative inference using entropy-weighted Sliced Wasserstein distances for reference selection and Goldilocks zone sampling, achieving 19% relative mAP@30 improvement on the NOVA brain MRI benchmark.
Pro²Assist uses multimodal egocentric perception from AR glasses to track fine-grained progress in long-horizon procedural tasks and deliver timely proactive assistance, outperforming baselines by over 21% in action understanding and up to 2.29x in timing accuracy.
AnchorSeg uses ordered query banks of latent reasoning tokens plus a spatial anchor token and a Token-Mask Cycle Consistency loss to achieve 67.7% gIoU and 68.1% cIoU on the ReasonSeg benchmark.
DeformPIC deforms query point clouds under prompt guidance for in-context learning, outperforming prior methods with lower Chamfer Distance on reconstruction, denoising, and registration tasks.
A new dataset and nine-metric majority-vote procedure show that existing code-reasoning benchmarks are dominated by lower-complexity problems that do not reflect real-world code.
ProAgent uses on-demand tiered perception and context-aware LLM reasoning to deliver proactive assistance on AR glasses, achieving up to 27.7% higher prediction accuracy and 20.5% lower false detections than baselines.
CREST-Search is a red-teaming framework that crafts seemingly benign search queries to induce unsafe citations from web-augmented LLMs, backed by a new WebSearch-Harm dataset for fine-tuning a specialized attacker model.
SITE applies soft gradient-based head selection to inject ICL-derived task embeddings, outperforming prior embedding adaptation and few-shot ICL across generation, reasoning, and NLU tasks on 12 LLMs from 4B to 70B parameters.
One training example via RLVR boosts LLM math reasoning from 17.6% to 35.7% average across six benchmarks.
CodeMind evaluates ten LLMs on four benchmarks using three new code reasoning tasks, finding performance varies by model size and drops with complexity while showing no correlation with bug repair ability.
Set-of-Mark prompting marks segmented image regions with alphanumerics and masks to let GPT-4V achieve state-of-the-art zero-shot results on referring expression comprehension and segmentation benchmarks like RefCOCOg.
Traj-Evolve combines non-parametric experience retrieval and multi-agent RL with a leave-one-out unification strategy to outperform baselines on lung cancer prediction from up to five years of multimodal EHRs, including in never-smokers.
CDS-trained BabyLMs show earlier and more appropriate production in a new frame-completion task while FineWeb-edu models lead on comprehension benchmarks, indicating current tests underestimate CDS benefits.
TCFDNet uses a Gait Modality Text Dictionary from LLMs, CLIP alignment, and text-guided disentanglement modules to achieve SOTA cross-modal gait recognition on SUSTech1K and FreeGait.
DIVE improves in-context vector distillation for medical report generation via decisive-token supervision on pathology terms and EOS plus state-conditioned dynamic steering, achieving top BLEU-4, ROUGE-L and RadGraph F1 on MIMIC-CXR and CheXpert Plus.
LLMs show instruction-following rates from 1% to 99% when instructions conflict with hardcoded pattern demonstrations, with output diversity as the main predictor of resistance.
METIS internalizes curriculum judgment in LLM reinforcement fine-tuning by predicting within-prompt reward variance via in-context learning and jointly optimizing with a self-judgment reward, yielding superior performance and up to 67% faster convergence across math, code, and agent benchmarks.
Introduces Personal VCL formalization and benchmark revealing LMM context gaps, plus an Agentic Context Bank baseline that boosts personalized visual reasoning.
Decompose and Recompose decomposes seen robotic demonstrations into skill-action alignments and recomposes them via visual-semantic retrieval and planning to enable zero-shot cross-task generalization.
Ctx2Skill uses a self-evolving multi-agent loop with Challenger, Reasoner, Judge, and Cross-time Replay to discover context-specific skills, improving task-solving rates on CL-bench benchmarks across models.
citing papers explorer
-
Child-directed speech facilitates production, not comprehension, in BabyLMs
CDS-trained BabyLMs show earlier and more appropriate production in a new frame-completion task while FineWeb-edu models lead on comprehension benchmarks, indicating current tests underestimate CDS benefits.
-
Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation
DIVE improves in-context vector distillation for medical report generation via decisive-token supervision on pathology terms and EOS plus state-conditioned dynamic steering, achieving top BLEU-4, ROUGE-L and RadGraph F1 on MIMIC-CXR and CheXpert Plus.
-
Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs
LLMs show instruction-following rates from 1% to 99% when instructions conflict with hardcoded pattern demonstrations, with output diversity as the main predictor of resistance.
-
Dual-Enhancement Product Bundling: Bridging Interactive Graph and Large Language Model
A graph-to-text paradigm with Dynamic Concept Binding Mechanism integrates interactive graphs and LLMs to recommend product bundles, yielding 6.3%-26.5% gains over baselines on POG, POG_dense, and Steam datasets.
-
Measuring Representation Robustness in Large Language Models for Geometry
LLMs display accuracy gaps of up to 14 percentage points on the same geometry problems solely due to representation choice, with vector forms consistently weakest and a convert-then-solve prompt helping only high-capacity models.
-
Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
A unified framework for LLM agent memory is benchmarked, with a new hybrid method outperforming state-of-the-art on standard tasks.
-
Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis
A new framework using Task Subspace Logit Attribution localizes attention heads specialized for task recognition and task learning in in-context learning, showing they align and rotate hidden states within a task subspace.
-
Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)
SSAS improves LLM sentiment prediction consistency and data quality by up to 30% on three review datasets via syntactic and semantic context assessment summarization.
-
SSA: Improving Performance With a Better Scoring Function
Replacing Softmax with Scaled Signed Averaging in transformer attention improves generalization under distribution shifts for in-context learning and boosts results on NLP benchmarks.
-
Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Question
Question interpretation diversity outperforms model diversity for LLM ensembling on binary QA tasks using majority voting.
-
Exploring Cross-lingual Latent Transplantation: Mutual Opportunities and Open Challenges
XTransplant empirically shows that cross-lingual latent transplantation yields mutual benefits for multilingual capability and cultural adaptability in LLMs, especially low-resource ones, while revealing underutilized model potential.
-
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
E2LLM uses encoder-based soft prompt compression for long contexts to improve LLM reasoning on tasks like summarization and QA while maintaining efficiency.
-
Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs
wSSAS is a two-phase deterministic framework that uses hierarchical text organization and SNR-based feature prioritization to improve clustering integrity, categorization accuracy, and reproducibility when applying LLMs to large review datasets.
-
LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs
Graph-based parsers outperform LLMs on supervised relation extraction as linguistic graph complexity grows with more relations per document.
-
Recent Advances in Multimodal Affective Computing: An NLP Perspective
Survey organizing multimodal affective computing research around four NLP tasks, method paradigms, datasets, evaluation protocols, and future directions while releasing a resource repository.
-
Benchmark Data Contamination of Large Language Models: A Survey
A survey reviewing benchmark data contamination in LLMs, its impact on evaluation, and alternative assessment approaches.
-
A Survey on Large Language Models for Code Generation
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.
-
Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.
-
A Comprehensive Overview of Large Language Models
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.