Show newer

An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training. (arXiv:2312.11819v2 [cs.LG] UPDATED) 

A Survey of Reasoning with Foundation Models. (arXiv:2312.11562v5 [cs.AI] UPDATED) 

Topic Bias in Emotion Classification. (arXiv:2312.09043v2 [cs.CL] UPDATED) 

Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs. (arXiv:2312.05934v2 [cs.AI] UPDATED) 

Enhancing Task-Oriented Dialogues with Chitchat: a Comparative Study Based on Lexical Diversity and Divergence. (arXiv:2311.14067v2 [cs.CL] UPDATED) 

General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level. (arXiv:2311.13892v3 [cs.CL] UPDATED) 

Meta Prompting for AGI Systems. (arXiv:2311.11482v2 [cs.AI] UPDATED) 

Leveraging Large Language Models for Collective Decision-Making. (arXiv:2311.04928v2 [cs.CL] UPDATED) 

Massive Editing for Large Language Models via Meta Learning. (arXiv:2311.04661v3 [cs.CL] UPDATED) 

ERNetCL: A novel emotion recognition network in textual conversation based on curriculum learning strategy. (arXiv:2308.06450v2 [cs.CL] UPDATED) 

Arithmetic with Language Models: from Memorization to Computation. (arXiv:2308.01154v2 [cs.AI] UPDATED) 

KoBBQ: Korean Bias Benchmark for Question Answering. (arXiv:2307.16778v2 [cs.CL] UPDATED) 

Disentanglement in a GAN for Unconditional Speech Synthesis. (arXiv:2307.01673v2 [eess.AS] UPDATED) 

What do self-supervised speech models know about words?. (arXiv:2307.00162v2 [cs.CL] UPDATED) 

A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling. (arXiv:2306.14806v2 [cs.CL] UPDATED) 

System-Level Natural Language Feedback. (arXiv:2306.13588v2 [cs.CL] UPDATED) 

Unifying Large Language Models and Knowledge Graphs: A Roadmap. (arXiv:2306.08302v3 [cs.CL] UPDATED) 

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation. (arXiv:2306.00789v4 [cs.CL] UPDATED) 

OpenPI2.0: An Improved Dataset for Entity Tracking in Texts. (arXiv:2305.14603v2 [cs.CL] UPDATED) 

Diffusion Language Models Generation Can Be Halted Early. (arXiv:2305.10818v3 [cs.LG] UPDATED) 

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.