Large language models are temporal and causal reasoners for video question answering
Large Language Models (LLMs) have shown remarkable performances on a wide range of
natural language understanding and generation tasks. We observe that the LLMs provide …
natural language understanding and generation tasks. We observe that the LLMs provide …
Legal syllogism prompting: Teaching large language models for legal judgment prediction
C Jiang, X Yang - … of the Nineteenth International Conference on …, 2023 - dl.acm.org
Legal syllogism is a form of deductive reasoning commonly used by legal professionals to
analyze cases. In this paper, we propose legal syllogism prompting (LoT), a simple …
analyze cases. In this paper, we propose legal syllogism prompting (LoT), a simple …
Taking advice from chatgpt
P Zhang - arXiv preprint arXiv:2305.11888, 2023 - arxiv.org
A growing literature studies how humans incorporate advice from algorithms. This study
examines an algorithm with millions of daily users: ChatGPT. In a preregistered study, 118 …
examines an algorithm with millions of daily users: ChatGPT. In a preregistered study, 118 …
Can language models teach? teacher explanations improve student performance via personalization
A hallmark property of explainable AI models is the ability to teach other agents,
communicating knowledge of how to perform a task. While Large Language Models (LLMs) …
communicating knowledge of how to perform a task. While Large Language Models (LLMs) …
Human-LLM collaborative annotation through effective verification of LLM labels
Large language models (LLMs) have shown remarkable performance across various natural
language processing (NLP) tasks, indicating their significant potential as data annotators …
language processing (NLP) tasks, indicating their significant potential as data annotators …
Explaincpe: A free-text explanation benchmark of chinese pharmacist examination
As ChatGPT and GPT-4 spearhead the development of Large Language Models (LLMs),
more researchers are investigating their performance across various tasks. But more …
more researchers are investigating their performance across various tasks. But more …
Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda
J Schneider - arXiv preprint arXiv:2404.09554, 2024 - arxiv.org
Generative AI (GenAI) marked a shift from AI being able to recognize to AI being able to
generate solutions for a wide variety of tasks. As the generated solutions and applications …
generate solutions for a wide variety of tasks. As the generated solutions and applications …
Can language models teach weaker agents? teacher explanations improve students via personalization
A hallmark property of explainable AI models is the ability to teach other agents,
communicating knowledge of how to perform a task. While Large Language Models (LLMs) …
communicating knowledge of how to perform a task. While Large Language Models (LLMs) …
Simple framework for interpretable fine-grained text classification
M Battogtokh, M Luck, C Davidescu… - European Conference on …, 2023 - Springer
Fine-grained text classification with similar and many labels is a challenge in practical
applications. Interpreting predictions in this context is particularly difficult. To address this …
applications. Interpreting predictions in this context is particularly difficult. To address this …
[PDF][PDF] Interpretable and Controllable Language Models
P Hase - 2024 - peterbhase.github.io
The field of machine learning has reached the point where learning systems now
accomplish complicated tasks that we cannot ourselves describe algorithmic solutions to …
accomplish complicated tasks that we cannot ourselves describe algorithmic solutions to …