English
Related papers

Related papers: Two Kinds of Recall

200 papers

While fine-tuning is the standard for injecting factual knowledge into large language models (LLMs), the mechanisms enabling reliable fact recall via unseen queries remain poorly understood. Common two-stage training strategies, which…

Computation and Language · Computer Science 2026-05-29 Ying Zhang , Benjamin Heinzerling , Dongyuan Li , Kentaro Inui

Three types of regression models researchers need to be familiar with and know the requirements of each: parametric, semiparametric and nonparametric regression models. The type of modeling used is based on how much information are…

Methodology · Statistics 2019-06-26 Hamdy F. F. Mahmoud

Generative models can have distinct mode of failures like mode dropping and low quality samples, which cannot be captured by a single scalar metric. To address this, recent works propose evaluating generative models using precision and…

Machine Learning · Computer Science 2023-02-03 Alexandre Verine , Benjamin Negrevergne , Muni Sreenivas Pydi , Yann Chevaleyre

Memory plays a pivotal role in enabling large language model~(LLM)-based agents to engage in complex and long-term interactions, such as question answering (QA) and dialogue systems. While various memory modules have been proposed for these…

Computation and Language · Computer Science 2024-12-23 Ruihong Zeng , Jinyuan Fang , Siwei Liu , Zaiqiao Meng

Truth discovery is to resolve conflicts and find the truth from multiple-source statements. Conventional methods mostly research based on the mutual effect between the reliability of sources and the credibility of statements, however, pay…

Computation and Language · Computer Science 2016-11-08 Luyang Li , Bing Qin , Wenjing Ren , Ting Liu

In recent years, model-free methods that use deep learning have achieved great success in many different reinforcement learning environments. Most successful approaches focus on solving a single task, while multi-task reinforcement learning…

Machine Learning · Computer Science 2017-05-25 Asier Mujika

This paper proposes bimorphic recursion, which is restricted polymorphic recursion such that every recursive call in the body of a function definition has the same type. Bimorphic recursion allows us to assign two different types to a…

Logic in Computer Science · Computer Science 2011-06-08 Makoto Tatsuta , Ferruccio Damiani

Binary classification involves predicting the label of an instance based on whether the model score for the positive class exceeds a threshold chosen based on the application requirements (e.g., maximizing recall for a precision bound).…

Machine Learning · Computer Science 2023-11-21 Gundeep Arora , Srujana Merugu , Anoop Saladi , Rajeev Rastogi

We leverage probabilistic models of neural representations to investigate how residual networks fit classes. To this end, we estimate class-conditional density models for representations learned by deep ResNets. We then use these models to…

Machine Learning · Computer Science 2022-12-02 Michał Jamroż , Marcin Kurdziel

A retrieval model should not only interpolate the training data but also extrapolate well to the queries that are different from the training data. While neural retrieval models have demonstrated impressive performance on ad-hoc search…

Information Retrieval · Computer Science 2022-08-05 Jingtao Zhan , Xiaohui Xie , Jiaxin Mao , Yiqun Liu , Jiafeng Guo , Min Zhang , Shaoping Ma

Traditional learning systems have responded quickly to the COVID pandemic and moved to online or distance learning. Online learning requires a personalization method because the interaction between learners and instructors is minimal, and…

Computers and Society · Computer Science 2022-09-27 Ahmad Mousa Altamimi , Mohammad Azzeh , Mahmoud Albashayreh

Reasoning in large language models is often discussed as a single capability, but some of its gains may stem from simpler underlying operations. We examine two such primitives, recall and state-tracking, through five controlled task…

Computation and Language · Computer Science 2026-05-27 Shivam Rawat , Lucie Flek , Florian Mai , Nicholas Kluge Corrêa

Human memory is inherently prone to forgetting. To address this, multimodal embedding models have been introduced, which transform diverse real-world data into a unified embedding space. These embeddings can be retrieved efficiently, aiding…

Information Retrieval · Computer Science 2024-09-25 Dongqi Cai , Shangguang Wang , Chen Peng , Zeling Zhang , Mengwei Xu

There are two main approaches to the distributed representation of words: low-dimensional deep learning embeddings and high-dimensional distributional models, in which each dimension corresponds to a context word. In this paper, we combine…

Computation and Language · Computer Science 2014-02-19 Irina Sergienya , Hinrich Schütze

Deep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradigm is still limited when facing the need to learn new…

Machine Learning · Computer Science 2018-11-16 Jing Shi , Jiaming Xu , Yiqun Yao , Bo Xu

Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF). Recent works indicate that CL is a complex topic, even more so when…

Machine Learning · Computer Science 2022-06-09 Benedikt Bagus , Alexander Gepperth

Many modern high-performing machine learning models such as GPT-3 primarily rely on scaling up models, e.g., transformer networks. Simultaneously, a parallel line of work aims to improve the model performance by augmenting an input instance…

Machine Learning · Computer Science 2022-10-07 Soumya Basu , Ankit Singh Rawat , Manzil Zaheer

Transformers can generate predictions in two approaches: 1. auto-regressively by conditioning each sequence element on the previous ones, or 2. directly produce an output sequences in parallel. While research has mostly explored upon this…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Andrea Alfieri , Yancong Lin , Jan C. van Gemert

World models power some of the most efficient reinforcement learning algorithms. In this work, we showcase that they can be harnessed for continual learning - a situation when the agent faces changing environments. World models typically…

For some classification scenarios, it is desirable to use only those classification instances that a trained model associates with a high certainty. To obtain such high-certainty instances, previous work has proposed accuracy-reject curves.…

Machine Learning · Computer Science 2024-03-15 Lydia Fischer , Patricia Wollstadt