Show newer
arXiv - CSCL

Syntax Error-Free and Generalizable Tool Use for LLMs via Finite-State Decoding. (arXiv:2310.07075v1 [cs.CL]) 

arxiv.org/abs/2310.07075

0
arXiv - CSCL

Large Language Models can Learn Rules. (arXiv:2310.07064v1 [cs.AI]) 

arxiv.org/abs/2310.07064

0
arXiv - CSCL

DKEC: Domain Knowledge Enhanced Multi-Label Classification for Electronic Health Records. (arXiv:2310.07059v1 [cs.CL]) 

arxiv.org/abs/2310.07059

0
arXiv - CSCL

Automatic Macro Mining from Interaction Traces at Scale. (arXiv:2310.07023v1 [cs.HC]) 

arxiv.org/abs/2310.07023

0
arXiv - CSCL

NEWTON: Are Large Language Models Capable of Physical Reasoning?. (arXiv:2310.07018v1 [cs.CL]) 

arxiv.org/abs/2310.07018

0
arXiv - CSCL

Answer Candidate Type Selection: Text-to-Text Language Model for Closed Book Question Answering Meets Knowledge Graphs. (arXiv:2310.07008v1 [cs.CL]) 

arxiv.org/abs/2310.07008

0
arXiv - CSCL

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation. (arXiv:2310.06987v1 [cs.CL]) 

arxiv.org/abs/2310.06987

0
arXiv - CSCL

Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models. (arXiv:2310.06983v1 [cs.CL]) 

arxiv.org/abs/2310.06983

0
arXiv - CSCL

Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings. (arXiv:2310.06977v1 [cs.CL]) 

arxiv.org/abs/2310.06977

0
arXiv - CSCL

Document-Level Supervision for Multi-Aspect Sentiment Analysis Without Fine-grained Labels. (arXiv:2310.06940v1 [cs.CL]) 

arxiv.org/abs/2310.06940

0
arXiv - CSCL

Sparse Finetuning for Inference Acceleration of Large Language Models. (arXiv:2310.06927v1 [cs.CL]) 

arxiv.org/abs/2310.06927

0
arXiv - CSCL

Improving Contrastive Learning of Sentence Embeddings with Focal-InfoNCE. (arXiv:2310.06918v1 [cs.CL]) 

arxiv.org/abs/2310.06918

0
arXiv - CSCL

A Comparative Study of Transformer-based Neural Text Representation Techniques on Bug Triaging. (arXiv:2310.06913v1 [cs.SE]) 

arxiv.org/abs/2310.06913

0
arXiv - CSCL

Exploiting Language Models as a Source of Knowledge for Cognitive Agents. (arXiv:2310.06846v1 [cs.AI]) 

arxiv.org/abs/2310.06846

0
arXiv - CSCL

An Empirical Study of AI Generated Text Detection Tools. (arXiv:2310.01423v1 [cs.CL] CROSS LISTED) 

arxiv.org/abs/2310.01423

0
arXiv - CSCL

An Empirical Study on Fertility Proposals Using Multi-Grained Topic Analysis Methods. (arXiv:2307.10025v2 [cs.HC] CROSS LISTED) 

arxiv.org/abs/2307.10025

0
arXiv - CSCL

REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction. (arXiv:2306.15724v3 [cs.RO] CROSS LISTED) 

arxiv.org/abs/2306.15724

0
arXiv - CSCL

DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning. (arXiv:2310.02954v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.02954

0
arXiv - CSCL

LC-Score: Reference-less estimation of Text Comprehension Difficulty. (arXiv:2310.02754v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.02754

0
arXiv - CSCL

On the definition of toxicity in NLP. (arXiv:2310.02357v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.02357

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