Related papers: Efficient rule induction by ignoring pointless rul…

This paper introduces a novel method, referred to as "hashing", which involves masking potentially bias-inducing words in large language models (LLMs) with hash-like meaningless identifiers to reduce cognitive biases and reliance on…

General Game Playing (GGP) is a framework in which an artificial intelligence program is required to play a variety of games successfully. It acts as a test bed for AI and motivator of research. The AI is given a random game description at…

This article introduces an imitation learning method for learning maximum entropy policies that comply with constraints demonstrated by expert trajectories executing a task. The formulation of the method takes advantage of results…

As AI systems become increasingly autonomous, aligning their decision-making to human preferences is essential. In domains like autonomous driving or robotics, it is impossible to write down the reward function representing these…

A logic programming paradigm which expresses solutions to problems as stable models has recently been promoted as a declarative approach to solving various combinatorial and search problems, including planning problems. In this paradigm,…

Large Language Models (LLMs) inevitably acquire harmful information during training on massive datasets. LLM unlearning aims to eliminate the influence of such harmful information while maintaining the model's overall performance. Existing…

Memory-based learning, keeping full memory of learning material, appears a viable approach to learning NLP tasks, and is often superior in generalisation accuracy to eager learning approaches that abstract from learning material. Here we…

We introduce a lazy approach to the explanation-based approximation of probabilistic logic programs. It uses only the most significant part of the program when searching for explanations. The result is a fast and anytime approximate…

Information removal or suppression in large language models (LLMs) is a desired functionality, useful in AI regulation, legal compliance, safety, and privacy. LLM unlearning methods aim to remove information on demand from LLMs. Current LLM…

We study how to perform unlearning, i.e. forgetting undesirable misbehaviors, on large language models (LLMs). We show at least three scenarios of aligning LLMs with human preferences can benefit from unlearning: (1) removing harmful…

In-context learning (ICL) has proven highly effective across diverse large language model (LLM) tasks. However, its potential for enhancing tasks that demand step-by-step logical deduction, such as mathematical reasoning, remains…

Inductions and game semantics are two useful extensions to traditional logic programming. To be specific, inductions can capture a wider class of provable formulas in logic programming. Adopting game semantics can make logic programming…

Machine unlearning is the process of efficiently removing specific information from a trained machine learning model without retraining from scratch. Existing unlearning methods, which often provide provable guarantees, typically involve…

Iterative learning control (ILC) improves the performance of a repetitive system by learning from previous trials. ILC can be combined with Model Predictive Control (MPC) to mitigate non-repetitive disturbances, thus improving overall…

Practitioners designing reinforcement learning policies face a fundamental challenge: translating intended behavioral objectives into representative reward functions. This challenge stems from behavioral intent requiring simultaneous…

Synthesizing large logic programs through symbolic Inductive Logic Programming (ILP) typically requires intermediate definitions. However, cluttering the hypothesis space with intensional predicates typically degrades performance. In…

Prompt Learning has recently gained great popularity in bridging the gap between pretraining tasks and various downstream tasks. It freezes Pretrained Language Models (PLMs) and only tunes a few task-related parameters (prompts) for…

Database indexes facilitate data retrieval and benefit broad applications in real-world systems. Recently, a new family of index, named learned index, is proposed to learn hidden yet useful data distribution and incorporate such information…

This paper presents null-shot prompting. Null-shot prompting exploits hallucination in large language models (LLMs) by instructing LLMs to utilize information from the "Examples" section that never exists within the provided context to…

In this book we promote logical computational linguistics as opposed to statistical computational linguistics. In particular, we provide a logical semantic interface. This book assembles more than twenty years of research work on type…