English
Related papers

Related papers: Information-Theoretic Probing with Minimum Descrip…

200 papers

In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples. Yet, how these models use the provided context remains opaque. While Chain-of-Thought prompting is widely used,…

Artificial Intelligence · Computer Science 2026-05-28 Carmen Quiles-Ramírez , Leticia L. Rodríguez , Nicolás Martorell , Natalia Díaz-Rodríguez

Declarative machine learning (ML) aims at the high-level specification of ML tasks or algorithms, and automatic generation of optimized execution plans from these specifications. The fundamental goal is to simplify the usage and/or…

Databases · Computer Science 2016-05-20 Matthias Boehm , Alexandre V. Evfimievski , Niketan Pansare , Berthold Reinwald

Demonstration learning aims to guide the prompt prediction via providing answered demonstrations in the few shot settings. Despite achieving promising results, existing work only concatenates the answered examples as demonstrations to the…

Machine Learning · Computer Science 2022-09-02 Sirui Wang , Kaiwen Wei , Hongzhi Zhang , Yuntao Li , Wei Wu

In this paper we discuss a method, which we call Minimum Conditional Description Length (MCDL), for estimating the parameters of a subset of sites within a Markov random field. We assume that the edges are known for the entire graph…

Information Theory · Computer Science 2016-02-25 Matthew G. Reyes , David L. Neuhoff

Learning the structure of Bayesian networks and causal relationships from observations is a common goal in several areas of science and technology. We show that the prequential minimum description length principle (MDL) can be used to…

Machine Learning · Computer Science 2021-07-13 Jorg Bornschein , Silvia Chiappa , Alan Malek , Rosemary Nan Ke

While Large Language Models (LLMs) have exhibited remarkable emergent capabilities through extensive pre-training, they still face critical limitations in generalizing to specialized domains and handling diverse linguistic variations, known…

Computation and Language · Computer Science 2025-05-28 Jinwu Hu , Zhitian Zhang , Guohao Chen , Xutao Wen , Chao Shuai , Wei Luo , Bin Xiao , Yuanqing Li , Mingkui Tan

Recently, efficient fine-tuning of large-scale pre-trained models has attracted increasing research interests, where linear probing (LP) as a fundamental module is involved in exploiting the final representations for task-dependent…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Mingze Gao , Qilong Wang , Zhenyi Lin , Pengfei Zhu , Qinghua Hu , Jingbo Zhou

In-context learning (ICL) has emerged as a successful paradigm for leveraging large language models (LLMs). However, it often struggles to generalize beyond the distribution of the provided demonstrations. A recent advancement in enhancing…

Computation and Language · Computer Science 2025-06-04 Ukyo Honda , Tatsushi Oka

Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consistency can become brittle under calibration--deployment…

Computation and Language · Computer Science 2026-04-20 Yanli Wang , Peng Kuang , Xiaoyu Han , Kaidi Xu , Haohan Wang

In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks by conditioning on a small set of input-output demonstrations, without any parameter updates. Although there have been many theoretical efforts to explain how…

Machine Learning · Computer Science 2026-03-23 Xuhan Tong , Yuchen Zeng , Jiawei Zhang

The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction. However, their effectiveness in in-context learning remains…

Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. To address this problem, NLP researchers have proposed a range of techniques to estimate LLM's confidence over facts. However, due to the lack of a…

Computation and Language · Computer Science 2024-11-28 Matéo Mahaut , Laura Aina , Paula Czarnowska , Momchil Hardalov , Thomas Müller , Lluís Màrquez

We proposed a Least Information theory (LIT) to quantify meaning of information in probability distribution changes, from which a new information retrieval model was developed. We observed several important characteristics of the proposed…

Information Retrieval · Computer Science 2012-05-03 Weimao Ke

The quantity of event logs available is increasing rapidly, be they produced by industrial processes, computing systems, or life tracking, for instance. It is thus important to design effective ways to uncover the information they contain.…

Databases · Computer Science 2018-07-06 Esther Galbrun , Peggy Cellier , Nikolaj Tatti , Alexandre Termier , Bruno Crémilleux

Instance-dependent Partial Label Learning (ID-PLL) aims to learn a multi-class predictive model given training instances annotated with candidate labels related to features, among which correct labels are hidden fixed but unknown. The…

Machine Learning · Computer Science 2024-10-29 Congyu Qiao , Ning Xu , Yihao Hu , Xin Geng

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…

Machine Learning · Computer Science 2020-07-20 Christian Haase-Schütz , Rainer Stal , Heinz Hertlein , Bernhard Sick

In safety-critical applications, language models should be able to characterize their uncertainty with meaningful probabilities. Many uncertainty quantification approaches require supervised data; however, finding suitable unseen…

Computation and Language · Computer Science 2026-05-14 Sophia Hager , Simon Zeng , Nicholas Andrews

The minimum description length (MDL) principle states that the best model to account for some data minimizes the sum of the lengths, in bits, of the descriptions of the model and the residual error. The description length is thus a…

Quantitative Methods · Quantitative Biology 2015-07-21 Peter T. Hraber , Bette T. Korber , Steven Wolinsky , Henry A. Erlich , Elizabeth A. Trachtenberg , Thomas B. Kepler

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…

Computation and Language · Computer Science 2025-12-16 Cheng Wang , Zeming Wei , Qin Liu , Muhao Chen

Through in-context learning (ICL), large-scale language models are effective few-shot learners without additional model fine-tuning. However, the ICL performance does not scale well with the number of available training samples as it is…

Computation and Language · Computer Science 2023-06-16 Hyunsoo Cho , Hyuhng Joon Kim , Junyeob Kim , Sang-Woo Lee , Sang-goo Lee , Kang Min Yoo , Taeuk Kim
‹ Prev 1 8 9 10 Next ›