Q-Probe: A Lightweight Approach to Reward Maximization for Language Models
The article introduces Q-probing, a method that adapts a pre-trained language model to maximize a task-specific reward…
Big data analytics to classify earthwork-related locations: A Chengdu study
This article discusses the use of big data analytics to classify earthwork-related locations (ERLs), which are significant…
On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
The article delves into the study of off-policy evaluation (OPE) in environments with complex observations, aiming to…
CaT-GNN: Enhancing Credit Card Fraud Detection via Causal Temporal Graph Neural Networks
The paper introduces a novel method for credit card fraud detection, the Causal Temporal Graph Neural Network…
Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learning
The article proposes a way to incorporate expert rules into machine learning models, specifically in the context…
Clifford-Steerable Convolutional Neural Networks
The article presents Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a new class of E(p, q)-equivariant CNNs. These networks…
How Transformers Learn Causal Structure with Gradient Descent
The study by Eshaan Nichani, Alex Damian, and Jason D. Lee from Princeton University investigates how transformers…
Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
This article discusses the application of Reinforcement Learning from Human Feedback (RLHF) in large language models (LLMs)….
Prompting a Pretrained Transformer Can Be a Universal Approximator
The paper delves into the theoretical understanding of fine-tuning methods such as prompting and prefix-tuning of transformer…
Generalising realisability in statistical learning theory under epistemic uncertainty
The paper delves into the concept of realisability in statistical learning theory under the assumption of epistemic…