Show newer

Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models. (arXiv:2310.10378v3 [cs.CL] UPDATED) 

AdaLomo: Low-memory Optimization with Adaptive Learning Rate. (arXiv:2310.10195v2 [cs.LG] UPDATED) 

In-Context Learning with Iterative Demonstration Selection. (arXiv:2310.09881v2 [cs.CL] UPDATED) 

Merging Experts into One: Improving Computational Efficiency of Mixture of Experts. (arXiv:2310.09832v2 [cs.CL] UPDATED) 

Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents. (arXiv:2310.09343v2 [cs.CL] UPDATED) 

A Zero-Shot Language Agent for Computer Control with Structured Reflection. (arXiv:2310.08740v3 [cs.CL] UPDATED) 

LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models. (arXiv:2310.08659v3 [cs.CL] UPDATED) 

Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation. (arXiv:2310.08395v3 [cs.CL] UPDATED) 

Fine-grained Conversational Decoding via Isotropic and Proximal Search. (arXiv:2310.08130v3 [cs.CL] UPDATED) 

Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models. (arXiv:2310.07611v2 [cs.CL] UPDATED) 

"A Tale of Two Movements": Identifying and Comparing Perspectives in #BlackLivesMatter and #BlueLivesMatter Movements-related Tweets using Weakly Supervised Graph-based Structured Prediction. (arXiv:2310.07155v2 [cs.CL] UPDATED) 

Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting. (arXiv:2310.07081v2 [cs.CL] UPDATED) 

Improving Contrastive Learning of Sentence Embeddings with Focal-InfoNCE. (arXiv:2310.06918v2 [cs.CL] UPDATED) 

Humans and language models diverge when predicting repeating text. (arXiv:2310.06408v2 [cs.CL] UPDATED) 

Hexa: Self-Improving for Knowledge-Grounded Dialogue System. (arXiv:2310.06404v2 [cs.CL] UPDATED) 

Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Models. (arXiv:2310.06374v2 [cs.CL] UPDATED) 

An Attribution Method for Siamese Encoders. (arXiv:2310.05703v2 [cs.CL] UPDATED) 

Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance. (arXiv:2310.05597v3 [cs.CL] UPDATED) 

InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations. (arXiv:2310.05592v2 [cs.CL] UPDATED) 

Establishing Trustworthiness: Rethinking Tasks and Model Evaluation. (arXiv:2310.05442v2 [cs.CL] 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.