Show newer
arXiv - CSCL

Beyond Extraction: Contextualising Tabular Data for Efficient Summarisation by Language Models. (arXiv:2401.02333v1 [cs.LG]) 

arxiv.org/abs/2401.02333

0
arXiv - CSCL

LLaVA-$\phi$: Efficient Multi-Modal Assistant with Small Language Model. (arXiv:2401.02330v1 [cs.CV]) 

arxiv.org/abs/2401.02330

0
arXiv - CSCL

Are LLMs Robust for Spoken Dialogues?. (arXiv:2401.02297v1 [cs.CL]) 

arxiv.org/abs/2401.02297

0
arXiv - CSCL

Rethinking Response Evaluation from Interlocutor's Eye for Open-Domain Dialogue Systems. (arXiv:2401.02256v1 [cs.CL]) 

arxiv.org/abs/2401.02256

0
arXiv - CSCL

L3Cube-IndicNews: News-based Short Text and Long Document Classification Datasets in Indic Languages. (arXiv:2401.02254v1 [cs.CL]) 

arxiv.org/abs/2401.02254

0
arXiv - CSCL

Joint Multi-Facts Reasoning Network For Complex Temporal Question Answering Over Knowledge Graph. (arXiv:2401.02212v1 [cs.CL]) 

arxiv.org/abs/2401.02212

0
arXiv - CSCL

DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models. (arXiv:2401.02208v1 [cs.CL]) 

arxiv.org/abs/2401.02208

0
arXiv - CSCL

Location Aware Modular Biencoder for Tourism Question Answering. (arXiv:2401.02187v1 [cs.CL]) 

arxiv.org/abs/2401.02187

0
arXiv - CSCL

Shayona@SMM4H23: COVID-19 Self diagnosis classification using BERT and LightGBM models. (arXiv:2401.02158v1 [cs.CL]) 

arxiv.org/abs/2401.02158

0
arXiv - CSCL

Exploring Boundary of GPT-4V on Marine Analysis: A Preliminary Case Study. (arXiv:2401.02147v1 [cs.CL]) 

arxiv.org/abs/2401.02147

0
arXiv - CSCL

DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models. (arXiv:2401.02132v1 [cs.CL]) 

arxiv.org/abs/2401.02132

0
arXiv - CSCL

PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble Techniques. (arXiv:2401.02122v1 [cs.CL]) 

arxiv.org/abs/2401.02122

0
arXiv - CSCL

Using LLM to select the right SQL Query from candidates. (arXiv:2401.02115v1 [cs.CL]) 

arxiv.org/abs/2401.02115

0
arXiv - CSCL

Re-evaluating the Memory-balanced Pipeline Parallelism: BPipe. (arXiv:2401.02088v1 [cs.LG]) 

arxiv.org/abs/2401.02088

0
arXiv - CSCL

ICE-GRT: Instruction Context Enhancement by Generative Reinforcement based Transformers. (arXiv:2401.02072v1 [cs.CL]) 

arxiv.org/abs/2401.02072

0
arXiv - CSCL

Understanding LLMs: A Comprehensive Overview from Training to Inference. (arXiv:2401.02038v1 [cs.CL]) 

arxiv.org/abs/2401.02038

0
arXiv - CSCL

Text2MDT: Extracting Medical Decision Trees from Medical Texts. (arXiv:2401.02034v1 [cs.CL]) 

arxiv.org/abs/2401.02034

0
arXiv - CSCL

Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives. (arXiv:2401.02009v1 [cs.CL]) 

arxiv.org/abs/2401.02009

0
arXiv - CSCL

Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias. (arXiv:2401.01989v1 [cs.CL]) 

arxiv.org/abs/2401.01989

0
arXiv - CSCL

A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity. (arXiv:2401.01967v1 [cs.CL]) 

arxiv.org/abs/2401.01967

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