Challenge: In-context learning (ICL) suffers from oversensitivity to the prompt, making it unreliable in real-world scenarios.
Approach: They propose a few-shot selective prediction method that abstains from sensitive predictions.
Outcome: The proposed method outperforms confidence-based and entropy-based methods on ten classification datasets.

Similar Papers

How are Prompts Different in Terms of Sensitivity? (2024.naacl-long)

Copied to clipboard

Challenge: In-context learning (ICL) has become one of the most popular learning paradigms due to the rapid development of large language models (LLMs).
Approach: They propose a prompt analysis based on sensitivity and introduce sensitivity-aware decoding which incorporates sensitivity estimation as a penalty term in the standard greedy decoding.
Outcome: The proposed approach is particularly useful when information in the input is scarce.
Mitigating Label Biases for In-context Learning (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to categorize label biases in in-context learning (ICL) have not addressed all three types of label bias.
Approach: They propose a method that estimates a language model’s label bias using random in-domain words from the task corpus to categorize and detect label biases in ICL.
Outcome: The proposed method significantly improves the performance of GPT-J and GPT-3 on a wide range of tasks.
In-context Learning and Gradient Descent Revisited (2024.naacl-long)

Copied to clipboard

Challenge: In-context learning (ICL) has shown impressive results in few-shot learning tasks, yet its underlying mechanism remains elusive.
Approach: They propose a simple gradient descent-based optimization procedure that respects layer causality and improves similarity scores significantly.
Outcome: The proposed procedure improves similarity scores on untrained models despite not showing ICL.
How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning (2024.emnlp-main)

Copied to clipboard

Challenge: In-context learning (ICL) is an emergent ability of large language models.
Approach: They propose to use in-context learning to predict sentences with semantically-unrelated labels on 1% heads to investigate the mechanism.
Outcome: The proposed methods reduce the majority label bias and recency bias by 22% and 17%, respectively.
Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations (2022.emnlp-main)

Copied to clipboard

Challenge: Intuitively, ground-truth labels should have as much impact in in-context learning as supervised learning, but the impact of the quality of demonstrations remains elusive.
Approach: They propose to measure input-label correspondence and ground-truth label effect ratio . they propose to use verbosity of prompt templates and language model size as controlling factors .
Outcome: The proposed metrics show that ground-truth labels have less impact than previously thought . the authors identify key components as controlling factors to achieve noise-resilient ICL .
A Study on the Calibration of In-context Learning (2024.naacl-long)

Copied to clipboard

Challenge: Prior research has demonstrated improvements in the calibration of language models (LMs) in-context learning is a popular method for adapting static LMs to safety-critical domains.
Approach: They use in-context learning to adapt static language models through tailored prompts to a wide range of tasks and find that miscalibration occurs in low-shot settings.
Outcome: The proposed calibrations show that models exhibit increased miscalibration before achieving better calibration in low-shot settings.
The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis (2024.emnlp-main)

Copied to clipboard

Challenge: In-context learning (ICL) is a capability that enables large language models to excel in proficiency through demonstration examples.
Approach: They present a survey on the interpretation and analysis of in-context learning . they focus on theoretical and empirical perspectives on the concept .
Outcome: The proposed model can perform tasks with minimal examples without re-training and has demonstrated proficiency across various tasks with a minimal set of task-oriented examples.
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning (2024.findings-emnlp)

Copied to clipboard

Challenge: Fine-tuning and in-context learning are two prevalent methods in imbuing large language models with task-specific knowledge.
Approach: They propose to use a circuit shift theory to explain why in-context learning is superior to fine-tuning for tasks with implicit patterns.
Outcome: The proposed method can grasp deep patterns and significantly improve accuracy on implicit patterns, compared with fine-tuning and in-context learning.
In-Context Learning (and Unlearning) of Length Biases (2025.naacl-long)

Copied to clipboard

Challenge: Existing work has demonstrated the ability of large language models to learn lexical and label biases in-context negatively impacts performance and robustness of models.
Approach: They investigate the impact of length biases on in-context learning by analyzing model length information in-constext.
Outcome: The proposed model learns length biases in the context window without parameter updates.
Large Language Models are Miscalibrated In-Context Learners (2025.findings-acl)

Copied to clipboard

Challenge: In-context Learning and Supervised Fine-Tuning have emerged as pre-dominant methodologies for machine learning and NLP.
Approach: They propose to use self-ensembling to improve both performance and calibration of language models.
Outcome: The proposed learning paradigms can achieve better calibration and better performance than the previous learning paradigm.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations