English
Related papers

Related papers: Redeeming Falsifiability?

200 papers

Generative models are trained with the simple objective of imitating the conditional probability distribution induced by the data they are trained on. Therefore, when trained on data generated by humans, we may not expect the artificial…

Machine Learning · Computer Science 2024-10-15 Edwin Zhang , Vincent Zhu , Naomi Saphra , Anat Kleiman , Benjamin L. Edelman , Milind Tambe , Sham M. Kakade , Eran Malach

One of the common ways children learn is by mimicking adults. Imitation learning focuses on learning policies with suitable performance from demonstrations generated by an expert, with an unspecified performance measure, and unobserved…

Machine Learning · Computer Science 2022-08-15 Junzhe Zhang , Daniel Kumor , Elias Bareinboim

Machine learning researchers and practitioners steadily enlarge the multitude of successful learning models. They achieve this through in-depth theoretical analyses and experiential heuristics. However, there is no known general-purpose…

Computational Complexity · Computer Science 2023-10-18 Matthias C. Caro

Corroboration or confirmation is a prominent philosophical debate of the 20th century. Many philosophers have been involved in this debate most notably the proponents of confirmation led by Hempel and its most powerful criticism by the…

History and Philosophy of Physics · Physics 2015-11-04 Roman Lukyanenko

Bayesian experts who are exposed to different evidence often make contradictory probabilistic forecasts. An aggregator, ignorant of the underlying model, uses this to calculate her own forecast. We use the notions of scoring rules and…

Economics · Quantitative Finance 2018-02-13 Itai Areili , Yakov Babichenko , Rann Smorodinsky

In a probability-based reasoning system, Bayes' theorem and its variations are often used to revise the system's beliefs. However, if the explicit conditions and the implicit conditions of probability assignments `me properly distinguished,…

Artificial Intelligence · Computer Science 2013-03-08 Pei Wang

Proof-of-Learning (PoL) proposes that a model owner logs training checkpoints to establish a proof of having expended the computation necessary for training. The authors of PoL forego cryptographic approaches and trade rigorous security…

Automatic fake news detection models are ostensibly based on logic, where the truth of a claim made in a headline can be determined by supporting or refuting evidence found in a resulting web query. These models are believed to be reasoning…

Computation and Language · Computer Science 2022-04-18 Ian Kelk , Benjamin Basseri , Wee Yi Lee , Richard Qiu , Chris Tanner

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…

Computation and Language · Computer Science 2025-03-18 Alihan Hüyük , Xinnuo Xu , Jacqueline Maasch , Aditya V. Nori , Javier González

Weighted Updating generalizes Bayesian updating, allowing for biased beliefs by weighting the likelihood function and prior distribution with positive real exponents. I provide a rigorous foundation for the model by showing that…

Probability · Mathematics 2016-02-09 Jesse Aaron Zinn

For AI systems to garner widespread public acceptance, we must develop methods capable of explaining the decisions of black-box models such as neural networks. In this work, we identify two issues of current explanatory methods. First, we…

Computation and Language · Computer Science 2019-12-06 Oana-Maria Camburu , Eleonora Giunchiglia , Jakob Foerster , Thomas Lukasiewicz , Phil Blunsom

The problem is to determine which processors are reliable in a remote location by asking "Yes or No" questions. The processors are of three types: those that always tell the truth, those that always lie, and those the sometimes tell the…

Other Computer Science · Computer Science 2014-07-24 Robert Cowen

This article introduces a new method for eliciting prior distributions from experts. The method models an expert decision-making process to infer a prior probability distribution for a rare event $A$. More specifically, assuming there…

Methodology · Statistics 2023-07-17 Julia R. Falconer , Eibe Frank , Devon L. L. Polaschek , Chaitanya Joshi

We motivate and describe a theory of belief in this paper. This theory is developed with the following view of human belief in mind. Consider the belief that an event E will occur (or has occurred or is occurring). An agent either…

Artificial Intelligence · Computer Science 2013-03-26 Yen-Teh Hsia

According to the probability ranking principle, the document set with the highest values of probability of relevance optimizes information retrieval effectiveness given the probabilities are estimated as accurately as possible. The key…

Information Retrieval · Computer Science 2011-08-30 Massimo Melucci

Statistical hypothesis testing serves as statistical evidence for scientific innovation. However, if the reported results are intentionally biased, hypothesis testing no longer controls the rate of false discovery. In particular, we study…

Methodology · Statistics 2018-10-12 Junpei Komiyama , Takanori Maehara

Easier access to the internet and social media has made disseminating information through online sources very easy. Sources like Facebook, Twitter, online news sites and personal blogs of self-proclaimed journalists have become significant…

Computation and Language · Computer Science 2021-09-28 Shaily Bhatt , Sakshi Kalra , Naman Goenka , Yashvardhan Sharma

We consider the problem of a principal who needs to elicit the true worth of an object she owns from an agent who has a unique ability to compute this information. The correctness of the information cannot be verified by the principal, so…

Computer Science and Game Theory · Computer Science 2020-09-15 Shani Alkobi , David Sarne , Erel Segal-Halevi , Tomer Sharbaf

Recent Language Models (LMs) have shown impressive capabilities in generating texts with the knowledge internalized in parameters. Yet, LMs often generate the factually incorrect responses to the given queries, since their knowledge may be…

Computation and Language · Computer Science 2023-10-20 Jinheon Baek , Soyeong Jeong , Minki Kang , Jong C. Park , Sung Ju Hwang

We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly. We first show that larger models are well-calibrated on diverse multiple choice and true/false…