Search Results for author: Amos Azaria

Found 24 papers, 3 papers with code

Word Sense Induction with Attentive Context Clustering

no code implementations NLP4DH (ICON) 2021 Moshe Stekel, Amos Azaria, Shai Gordin

In this paper, we present ACCWSI (Attentive Context Clustering WSI), a method for Word Sense Induction, suitable for languages with limited resources.

Clustering Word Sense Induction

Ruffle&Riley: Towards the Automated Induction of Conversational Tutoring Systems

no code implementations26 Sep 2023 Robin Schmucker, Meng Xia, Amos Azaria, Tom Mitchell

Conversational tutoring systems (CTSs) offer learning experiences driven by natural language interaction.

Performance of ChatGPT-3.5 and GPT-4 on the United States Medical Licensing Examination With and Without Distractions

no code implementations12 Sep 2023 Myriam Safrai, Amos Azaria

The analysis results demonstrate that the ability of ChatGPT-3. 5 to answer correctly was impaired when small talk was added to medical data for multiple-choice questions (72. 1\% vs. 68. 9\%) and open questions (61. 5\% vs. 44. 3\%; p=0. 01), respectively.

Multiple-choice Sentence

ChatGPT is a Remarkable Tool -- For Experts

no code implementations2 Jun 2023 Amos Azaria, Rina Azoulay, Shulamit Reches

This paper investigates the capabilities of ChatGPT as an automated assistant in diverse domains, including scientific writing, mathematics, education, programming, and healthcare.

Logical Reasoning

The Internal State of an LLM Knows When It's Lying

1 code implementation26 Apr 2023 Amos Azaria, Tom Mitchell

While Large Language Models (LLMs) have shown exceptional performance in various tasks, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone.

Sentence

Meta-Reinforcement Learning Using Model Parameters

no code implementations27 Oct 2022 Gabriel Hartmann, Amos Azaria

In meta-reinforcement learning, an agent is trained in multiple different environments and attempts to learn a meta-policy that can efficiently adapt to a new environment.

Meta Reinforcement Learning reinforcement-learning +1

Criticality-Based Varying Step-Number Algorithm for Reinforcement Learning

no code implementations13 Jan 2022 Yitzhak Spielberg, Amos Azaria

In the context of reinforcement learning we introduce the concept of criticality of a state, which indicates the extent to which the choice of action in that particular state influences the expected return.

Q-Learning reinforcement-learning +1

The Concept of Criticality in AI Safety

no code implementations12 Jan 2022 Yitzhak Spielberg, Amos Azaria

When AI agents don't align their actions with human values they may cause serious harm.

Revelation of Task Difficulty in AI-aided Education

no code implementations12 Jan 2022 Yitzhak Spielberg, Amos Azaria

When a student is asked to perform a given task, her subjective estimate of the difficulty of that task has a strong influence on her performance.

Explaining Ridesharing: Selection of Explanations for Increasing User Satisfaction

no code implementations26 May 2021 David Zar, Noam Hazon, Amos Azaria

One possible way for increasing user satisfaction is by providing appropriate explanations comparing the alternative modes of transportation, such as a private taxi ride and public transportation.

Conversational Neuro-Symbolic Commonsense Reasoning

1 code implementation17 Jun 2020 Forough Arabshahi, Jennifer Lee, Mikayla Gawarecki, Kathryn Mazaitis, Amos Azaria, Tom Mitchell

More precisely, we consider the problem of identifying the unstated presumptions of the speaker that allow the requested action to achieve the desired goal from the given state (perhaps elaborated by making the implicit presumptions explicit).

Fiction Sentence Expansion and Enhancement via Focused Objective and Novelty Curve Sampling

no code implementations2 Dec 2019 Yuri Safovich, Amos Azaria

We describe the task of sentence expansion and enhancement, in which a sentence provided by a human is expanded in some creative way.

Sentence Sentence Expansion

AI for Explaining Decisions in Multi-Agent Environments

no code implementations10 Oct 2019 Sarit Kraus, Amos Azaria, Jelena Fiosina, Maike Greve, Noam Hazon, Lutz Kolbe, Tim-Benjamin Lembcke, Jörg P. Müller, Sören Schleibaum, Mark Vollrath

Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known.

Fairness

Learning to Conceal: A Deep Learning Based Method for Preserving Privacy and Avoiding Prejudice

no code implementations19 Sep 2019 Moshe Hanukoglu, Nissan Goldberg, Aviv Rovshitz, Amos Azaria

Namely, we created a variational autoencoder (VAE) model that is trained on a dataset including labels of the information one would like to conceal (e. g. gender, ethnicity, age).

Privacy Preserving

InstructableCrowd: Creating IF-THEN Rules for Smartphones via Conversations with the Crowd

no code implementations12 Sep 2019 Ting-Hao 'Kenneth' Huang, Amos Azaria, Oscar J. Romero, Jeffrey P. Bigham

The user verbally expresses a problem to the system, in which a group of crowd workers collectively respond and program relevant multi-part IF-THEN rules to help the user.

The Concept of Criticality in Reinforcement Learning

no code implementations16 Oct 2018 Yitzhak Spielberg, Amos Azaria

This observation is related to the idea that each state of the MDP has a certain measure of criticality which indicates how much the choice of the action in that state influences the return.

reinforcement-learning Reinforcement Learning (RL)

Goldbach's Function Approximation Using Deep Learning

no code implementations25 Mar 2018 Avigail Stekel, Merav Chkroun, Amos Azaria

Goldbach conjecture is one of the most famous open mathematical problems.

"Is there anything else I can help you with?": Challenges in Deploying an On-Demand Crowd-Powered Conversational Agent

no code implementations10 Aug 2017 Ting-Hao Kenneth Huang, Walter S. Lasecki, Amos Azaria, Jeffrey P. Bigham

To address this problem, we developed a crowd-powered conversational assistant, Chorus, and deployed it to see how users and workers would interact together when mediated by the system.

Sentence

The DARPA Twitter Bot Challenge

no code implementations20 Jan 2016 V. S. Subrahmanian, Amos Azaria, Skylar Durst, Vadim Kagan, Aram Galstyan, Kristina Lerman, Linhong Zhu, Emilio Ferrara, Alessandro Flammini, Filippo Menczer, Andrew Stevens, Alexander Dekhtyar, Shuyang Gao, Tad Hogg, Farshad Kooti, Yan Liu, Onur Varol, Prashant Shiralkar, Vinod Vydiswaran, Qiaozhu Mei, Tim Hwang

A number of organizations ranging from terrorist groups such as ISIS to politicians and nation states reportedly conduct explicit campaigns to influence opinion on social media, posing a risk to democratic processes.

Cannot find the paper you are looking for? You can Submit a new open access paper.