Membership Inference Attacks against Language Models via Neighbourhood Comparison. (arXiv:2305.18462v1 [cs.CL])
Taming AI Bots: Controllability of Neural States in Large Language Models. (arXiv:2305.18449v1 [cs.AI])
Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR. (arXiv:2305.18419v1 [cs.CL])
Understanding Breast Cancer Survival: Using Causality and Language Models on Multi-omics Data. (arXiv:2305.18410v1 [cs.LG])
Conformal Prediction with Large Language Models for Multi-Choice Question Answering. (arXiv:2305.18404v1 [cs.CL])
LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformers. (arXiv:2305.18396v1 [cs.LG])
Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks. (arXiv:2305.18395v1 [cs.CL])
MemeGraphs: Linking Memes to Knowledge Graphs. (arXiv:2305.18391v1 [cs.LG])
Emergent Modularity in Pre-trained Transformers. (arXiv:2305.18390v1 [cs.CL])
KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models. (arXiv:2305.18373v1 [cs.CV])
What indeed can GPT models do in chemistry? A comprehensive benchmark on eight tasks. (arXiv:2305.18365v1 [cs.CL])
DeepSI: Interactive Deep Learning for Semantic Interaction. (arXiv:2305.18357v1 [cs.LG])
LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations. (arXiv:2305.18354v1 [cs.CL])
Towards Open-World Product Attribute Mining: A Lightly-Supervised Approach. (arXiv:2305.18350v1 [cs.LG])
Neural Task Synthesis for Visual Programming. (arXiv:2305.18342v1 [cs.LG])
Mapping ChatGPT in Mainstream Media: Early Quantitative Insights through Sentiment Analysis and Word Frequency Analysis. (arXiv:2305.18340v1 [cs.CY])
A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutions. (arXiv:2305.18339v1 [cs.CY])
#REVAL: a semantic evaluation framework for hashtag recommendation. (arXiv:2305.18330v1 [cs.IR])
Regex-augmented Domain Transfer Topic Classification based on a Pre-trained Language Model: An application in Financial Domain. (arXiv:2305.18324v1 [cs.CL])
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models. (arXiv:2305.18323v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl