Show newer
arXiv - CSCL

True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4. (arXiv:2212.10114v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10114

0
arXiv - CSCL

When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods. (arXiv:2212.10025v2 [cs.LG] UPDATED) 

arxiv.org/abs/2212.10025

0
arXiv - CSCL

Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text. (arXiv:2211.11300v3 [cs.CL] UPDATED) 

arxiv.org/abs/2211.11300

0
arXiv - CSCL

Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA. (arXiv:2211.07516v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.07516

0
arXiv - CSCL

Easy Guided Decoding in Providing Suggestions for Interactive Machine Translation. (arXiv:2211.07093v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.07093

0
arXiv - CSCL

REV: Information-Theoretic Evaluation of Free-Text Rationales. (arXiv:2210.04982v5 [cs.CL] UPDATED) 

arxiv.org/abs/2210.04982

0
arXiv - CSCL

Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization. (arXiv:2210.04492v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.04492

0
arXiv - CSCL

ThinkSum: Probabilistic reasoning over sets using large language models. (arXiv:2210.01293v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.01293

0
arXiv - CSCL

BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models. (arXiv:2206.14268v3 [cs.CL] UPDATED) 

arxiv.org/abs/2206.14268

0
arXiv - CSCL

PhysNLU: A Language Resource for Evaluating Natural Language Understanding and Explanation Coherence in Physics. (arXiv:2201.04275v3 [cs.CL] UPDATED) 

arxiv.org/abs/2201.04275

0
arXiv - CSCL

Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling. (arXiv:2104.07704v2 [cs.CL] UPDATED) 

arxiv.org/abs/2104.07704

0
arXiv - CSCL

Lessons on Parameter Sharing across Layers in Transformers. (arXiv:2104.06022v4 [cs.CL] UPDATED) 

arxiv.org/abs/2104.06022

0
arXiv - CSCL

Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans. (arXiv:2306.01729v1 [cs.CL]) 

arxiv.org/abs/2306.01729

0
arXiv - CSCL

Distilling Efficient Language-Specific Models for Cross-Lingual Transfer. (arXiv:2306.01709v1 [cs.CL]) 

arxiv.org/abs/2306.01709

0
arXiv - CSCL

Resolving Interference When Merging Models. (arXiv:2306.01708v1 [cs.LG]) 

arxiv.org/abs/2306.01708

0
arXiv - CSCL

Learning Multi-step Reasoning from Arithmetic Task. (arXiv:2306.01707v1 [cs.CL]) 

arxiv.org/abs/2306.01707

0
arXiv - CSCL

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training. (arXiv:2306.01693v1 [cs.CL]) 

arxiv.org/abs/2306.01693

0
arXiv - CSCL

DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation. (arXiv:2306.01657v1 [cs.CL]) 

arxiv.org/abs/2306.01657

0
arXiv - CSCL

Learning from Partially Annotated Data: Example-aware Creation of Gap-filling Exercises for Language Learning. (arXiv:2306.01584v1 [cs.CL]) 

arxiv.org/abs/2306.01584

0
arXiv - CSCL

EmoUS: Simulating User Emotions in Task-Oriented Dialogues. (arXiv:2306.01579v1 [cs.CL]) 

arxiv.org/abs/2306.01579

0
Show older
Qoto Mastodon

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

Trending now

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy