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.

Similar Papers

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.
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.
Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective (2026.acl-long)

Copied to clipboard

Challenge: Prior studies comparing FT and ICL have yielded mixed and inconclusive results due to inconsistent experimental setups.
Approach: They propose a formal language learning task with precise language boundaries, controlled string sampling, and no data contamination to enable a rigorous comparison.
Outcome: The proposed task offers precise language boundaries, controlled string sampling, and no data contamination.
Exploring the Relationship between In-Context Learning and Instruction Tuning (2024.findings-emnlp)

Copied to clipboard

Challenge: In-Context Learning (ICL) and Instruction Tuning (IT) are two primary paradigms of adopting Large Language Models (LLMs) to downstream applications, but they are significantly different.
Approach: They examine how the hidden states of Large Language Models change in these two paradigms by examining how they differ in implementation.
Outcome: The proposed model changes the hidden states of LLMs as if its accompanying demonstrations were used to instructionally tune the model.
Ensemble-Instruct: Instruction Tuning Data Generation with a Heterogeneous Mixture of LMs (2023.findings-emnlp)

Copied to clipboard

Challenge: Empirical studies with different instruction-tuned LMs show that our proposed method yields higher-quality instruction tuning data than Self-Instruct.
Approach: They propose to use in-context learning techniques to train strong conversational agents . they propose to categorize and simplify ICL templates to make prompt learning easier .
Outcome: Empirical results show that the proposed method yields higher-quality instruction tuning data than Self-Instruct and improves performance of both vanilla and instruction-tuned LMs.
Large Language Models Are Overconfident in Their Own Responses (2026.findings-acl)

Copied to clipboard

Challenge: Prior work has shown that instruction-tuned large language models are less well calibrated than their base pre-trained counterparts.
Approach: They propose a simple inference-time strategy that frams the model’s answer as user input during confidence elicitation.
Outcome: The proposed approach reduces overconfidence and improves calibration by up to 26% without retraining.
How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have demonstrated that In-Context Learning (ICA) can align Large Language Models (LLMs) with human preferences without requiring parameter adjustments.
Approach: They investigate the effectiveness of each part in enabling ICA to function effectively and examine how variants in these parts impact alignment performance.
Outcome: The proposed model can comprehend human instructions without parameter adjustments.
Tutor-ICL: Guiding Large Language Models for Improved In-Context Learning Performance (2024.findings-emnlp)

Copied to clipboard

Challenge: In-context learning (ICL) is a dominant paradigm in natural language processing.
Approach: They propose a prompting method for classification tasks using exemplar answers in a *comparative format' they also propose introducing a test instance before the exemplars to improve performance .
Outcome: The proposed method achieves up to 13.76% increase in accuracy on classification tasks across decoder-only and encoder-decoder LLMs.
Investigating the Multilingual Calibration Effects of Language Model Instruction Tuning (2026.eacl-short)

Copied to clipboard

Challenge: despite advances in foundation model research, the relationship between large language models and their calibration remains an open area of research.
Approach: They examine a gap in the calibration of large language models within multilingual settings to better understand how data scarcity can potentially lead to different calibration effects.
Outcome: The proposed calibration gap is found in two multilingual benchmarks over 29 and 42 languages.
Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning (2024.findings-naacl)

Copied to clipboard

Challenge: Existing studies have explored multiple aspects that affect the performance of large language models (LLMs) such as input-output mapping, extensive data resources, and the ability to train on labeled examples.
Approach: They propose a framework that injects knowledge into LLMs during continual self-supervised pre-training and judiciously selects examples with high knowledge relevance.
Outcome: The proposed framework outperforms baseline models and improves by more than 13% and 7% on text classification and question-answering tasks.

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