Trained Transformers Learn Linear Models In-Context. (arXiv:2306.09927v1 [stat.ML])
Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions. (arXiv:2306.09922v1 [cs.RO])
No Strong Feelings One Way or Another: Re-operationalizing Neutrality in Natural Language Inference. (arXiv:2306.09918v1 [cs.CL])
Demystifying GPT Self-Repair for Code Generation. (arXiv:2306.09896v1 [cs.CL])
Revealing the impact of social circumstances on the selection of cancer therapy through natural language processing of social work notes. (arXiv:2306.09877v1 [cs.CL])
Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models. (arXiv:2306.09869v1 [cs.CV])
Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation From Deductive, Inductive and Abductive Views. (arXiv:2306.09841v1 [cs.CL])
Sheffield's Submission to the AmericasNLP Shared Task on Machine Translation into Indigenous Languages. (arXiv:2306.09830v1 [cs.CL])
Process Knowledge-infused Learning for Clinician-friendly Explanations. (arXiv:2306.09824v1 [cs.CL])
Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System. (arXiv:2306.09821v1 [cs.CL])
Investigating the Utility of Surprisal from Large Language Models for Speech Synthesis Prosody. (arXiv:2306.09814v1 [eess.AS])
RED$^{\rm FM}$: a Filtered and Multilingual Relation Extraction Dataset. (arXiv:2306.09802v1 [cs.CL])
Full Parameter Fine-tuning for Large Language Models with Limited Resources. (arXiv:2306.09782v1 [cs.CL])
Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models. (arXiv:2306.09752v1 [cs.CL])
Using Natural Language Processing and Networks to Automate Structured Literature Reviews: An Application to Farmers Climate Change Adaptation. (arXiv:2306.09737v1 [cs.CL])
Discourse Representation Structure Parsing for Chinese. (arXiv:2306.09725v1 [cs.CL])
Pushing the Limits of ChatGPT on NLP Tasks. (arXiv:2306.09719v1 [cs.CL])
Semi-Offline Reinforcement Learning for Optimized Text Generation. (arXiv:2306.09712v1 [cs.LG])
Reducing Computational Costs in Sentiment Analysis: Tensorized Recurrent Networks vs. Recurrent Networks. (arXiv:2306.09705v1 [cs.LG])
Cross-corpus Readability Compatibility Assessment for English Texts. (arXiv:2306.09704v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl