Copertina

Deconstructing In-Context Learning: Understanding Prompts via Corruption

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shivagunde, Namrata, Lialin, Vladislav, Muckatira, Sherin, Rumshisky, Anna
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training
di: Shivagunde, Namrata, et al.
Pubblicazione: (2026)

Emergent Abilities in Reduced-Scale Generative Language Models
di: Muckatira, Sherin, et al.
Pubblicazione: (2024)

A Pre-Training Analogue of Grokking in Language Models: Tracing Delayed Grammatical Generalization
di: Muckatira, Sherin, et al.
Pubblicazione: (2026)

Playing with Words, Improving with Rewards: Training Language Models for Creative Association
di: Deshpande, Vijeta, et al.
Pubblicazione: (2026)

Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning
di: Lialin, Vladislav, et al.
Pubblicazione: (2023)

NarrativeTime: Dense Temporal Annotation on a Timeline
di: Rogers, Anna, et al.
Pubblicazione: (2019)

Analysis of student understanding in short‐answer explanations to concept questions using a human‐centered AI approach
di: Harpreet Auby, et al.
Pubblicazione: (2025)

Prompt Perturbation Consistency Learning for Robust Language Models
di: Qiang, Yao, et al.
Pubblicazione: (2024)

A Penalty Goes a Long Way: Measuring Lexical Diversity in Synthetic Texts Under Prompt-Influenced Length Variations
di: Deshpande, Vijeta, et al.
Pubblicazione: (2025)

Assessing Generalization for Subpopulation Representative Modeling via In-Context Learning
di: Simmons, Gabriel, et al.
Pubblicazione: (2024)

Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting
di: Beck, Tilman, et al.
Pubblicazione: (2023)

Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Models
di: Deshpande, Vijeta, et al.
Pubblicazione: (2025)

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection
di: Deshpande, Vijeta, et al.
Pubblicazione: (2026)

Large Language Model Unlearning via Embedding-Corrupted Prompts
di: Liu, Chris Yuhao, et al.
Pubblicazione: (2024)

Prompt Optimization via Adversarial In-Context Learning
di: Do, Xuan Long, et al.
Pubblicazione: (2023)

AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption
di: Wang, Yanting, et al.
Pubblicazione: (2025)

Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
di: Blau, Tsachi, et al.
Pubblicazione: (2024)

Understanding In-Context Learning from Repetitions
di: Yan, Jianhao, et al.
Pubblicazione: (2023)

Understanding and Mitigating Dataset Corruption in LLM Steering
di: Anderson, Cullen, et al.
Pubblicazione: (2026)

Order Matters: Rethinking Prompt Construction in In-Context Learning
di: Li, Warren, et al.
Pubblicazione: (2025)

Enhancing LLM Problem Solving with REAP: Reflection, Explicit Problem Deconstruction, and Advanced Prompting
di: Lingo, Ryan, et al.
Pubblicazione: (2024)

Prompts Matter: Comparing ML/GAI Approaches for Generating Inductive Qualitative Coding Results
di: Chen, John, et al.
Pubblicazione: (2024)

Understanding the Prompt Sensitivity
di: Liu, Yang, et al.
Pubblicazione: (2026)

Understanding Synthetic Context Extension via Retrieval Heads
di: Zhao, Xinyu, et al.
Pubblicazione: (2024)

EndPrompt: Efficient Long-Context Extension via Terminal Anchoring
di: Tian, Han, et al.
Pubblicazione: (2026)

Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach
di: Fan, Sinan, et al.
Pubblicazione: (2025)

A Survey to Recent Progress Towards Understanding In-Context Learning
di: Mao, Haitao, et al.
Pubblicazione: (2024)

Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning
di: Doan, Nhi Hoai, et al.
Pubblicazione: (2025)

LUNA: A Framework for Language Understanding and Naturalness Assessment
di: Saidov, Marat, et al.
Pubblicazione: (2024)

Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models
di: Wang, Yiming, et al.
Pubblicazione: (2023)

MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs
di: Zhou, Yuhang, et al.
Pubblicazione: (2025)

Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning
di: Lin, Jingyang, et al.
Pubblicazione: (2025)

Understanding the Effects of Iterative Prompting on Truthfulness
di: Krishna, Satyapriya, et al.
Pubblicazione: (2024)

Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression
di: Li, Xinze, et al.
Pubblicazione: (2024)

The Power of Adaptation: Boosting In-Context Learning through Adaptive Prompting
di: Cai, Shuzhang, et al.
Pubblicazione: (2024)

Structured Prompt Language: Declarative Context Management for LLMs
di: Gong, Wen G.
Pubblicazione: (2026)

Towards Better Understanding of In-Context Learning Ability from In-Context Uncertainty Quantification
di: Liu, Shang, et al.
Pubblicazione: (2024)

PromptCL: Improving Event Representation via Prompt Template and Contrastive Learning
di: Feng, Yubo, et al.
Pubblicazione: (2024)

Emulating Retrieval Augmented Generation via Prompt Engineering for Enhanced Long Context Comprehension in LLMs
di: Park, Joon, et al.
Pubblicazione: (2025)

Slang Context-based Inference Enhancement via Greedy Search-Guided Chain-of-Thought Prompting
di: Cao, Jinghan, et al.
Pubblicazione: (2026)