Show more
arXiv - CSCL

Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization. (arXiv:2311.09335v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.09335

0
arXiv - CSCL

Knowledge Graph Construction in Power Distribution Networks. (arXiv:2311.08724v3 [cs.CL] UPDATED) 

arxiv.org/abs/2311.08724

0
arXiv - CSCL

A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering. (arXiv:2311.07536v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.07536

0
arXiv - CSCL

Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs. (arXiv:2311.04892v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.04892

0
arXiv - CSCL

Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction. (arXiv:2311.04507v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.04507

0
arXiv - CSCL

GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling. (arXiv:2311.01927v2 [cs.LG] UPDATED) 

arxiv.org/abs/2311.01927

0
arXiv - CSCL

An Open Source Data Contamination Report for Large Language Models. (arXiv:2310.17589v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.17589

0
arXiv - CSCL

Establishing Vocabulary Tests as a Benchmark for Evaluating Large Language Models. (arXiv:2310.14703v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.14703

0
arXiv - CSCL

Reconstructing Materials Tetrahedron: Challenges in Materials Information Extraction. (arXiv:2310.08383v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.08383

0
arXiv - CSCL

BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations. (arXiv:2310.07276v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.07276

0
arXiv - CSCL

Low-Resource Languages Jailbreak GPT-4. (arXiv:2310.02446v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.02446

0
arXiv - CSCL

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs. (arXiv:2310.01801v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.01801

0
arXiv - CSCL

Syllable-level lyrics generation from melody exploiting character-level language model. (arXiv:2310.00863v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.00863

0
arXiv - CSCL

Towards LLM-guided Causal Explainability for Black-box Text Classifiers. (arXiv:2309.13340v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.13340

0
arXiv - CSCL

Media of Langue: The dictionary that visualizes Inter-Lingual Semantic Network/Space. (arXiv:2309.08609v3 [cs.CL] UPDATED) 

arxiv.org/abs/2309.08609

0
arXiv - CSCL

Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding. (arXiv:2309.07098v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.07098

0
arXiv - CSCL

Breaking through the learning plateaus of in-context learning in Transformer. (arXiv:2309.06054v2 [cs.LG] UPDATED) 

arxiv.org/abs/2309.06054

0
arXiv - CSCL

Manifold-based Verbalizer Space Re-embedding for Tuning-free Prompt-based Classification. (arXiv:2309.04174v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.04174

0
arXiv - CSCL

Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation. (arXiv:2308.10335v5 [cs.CL] UPDATED) 

arxiv.org/abs/2308.10335

0
arXiv - CSCL

Learning the meanings of function words from grounded language using a visual question answering model. (arXiv:2308.08628v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.08628

0
Show more
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…