Show newer
arXiv - CSCL

Universal Self-Adaptive Prompting. (arXiv:2305.14926v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14926

0
arXiv - CSCL

Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory. (arXiv:2305.14889v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14889

0
arXiv - CSCL

Debiasing Made State-of-the-art: Revisiting the Simple Seed-based Weak Supervision for Text Classification. (arXiv:2305.14794v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14794

0
arXiv - CSCL

Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization. (arXiv:2305.14760v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14760

0
arXiv - CSCL

Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewriting. (arXiv:2305.14755v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14755

0
arXiv - CSCL

ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning. (arXiv:2305.14740v2 [cs.AI] UPDATED) 

arxiv.org/abs/2305.14740

0
arXiv - CSCL

Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection. (arXiv:2305.14735v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14735

0
arXiv - CSCL

Gender Biases in Automatic Evaluation Metrics for Image Captioning. (arXiv:2305.14711v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14711

0
arXiv - CSCL

You Are What You Annotate: Towards Better Models through Annotator Representations. (arXiv:2305.14663v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14663

0
arXiv - CSCL

COMET-M: Reasoning about Multiple Events in Complex Sentences. (arXiv:2305.14617v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14617

0
arXiv - CSCL

Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings. (arXiv:2305.14576v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14576

0
arXiv - CSCL

Sources of Hallucination by Large Language Models on Inference Tasks. (arXiv:2305.14552v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14552

0
arXiv - CSCL

MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems. (arXiv:2305.14536v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14536

0
arXiv - CSCL

NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders. (arXiv:2305.14499v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14499

0
arXiv - CSCL

Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment. (arXiv:2305.14492v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14492

0
arXiv - CSCL

Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA. (arXiv:2305.14458v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14458

0
arXiv - CSCL

Automatic Model Selection with Large Language Models for Reasoning. (arXiv:2305.14333v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14333

0
arXiv - CSCL

TalkUp: Paving the Way for Understanding Empowering Language. (arXiv:2305.14326v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14326

0
arXiv - CSCL

LLM-powered Data Augmentation for Enhanced Cross-lingual Performance. (arXiv:2305.14288v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14288

0
arXiv - CSCL

Query Rewriting for Retrieval-Augmented Large Language Models. (arXiv:2305.14283v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14283

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