Show newer
arXiv - CSCL

In-Context Learning Learns Label Relationships but Is Not Conventional Learning. (arXiv:2307.12375v3 [cs.CL] UPDATED) 

arxiv.org/abs/2307.12375

0
arXiv - CSCL

Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs. (arXiv:2307.10490v4 [cs.CR] UPDATED) 

arxiv.org/abs/2307.10490

0
arXiv - CSCL

In-context Autoencoder for Context Compression in a Large Language Model. (arXiv:2307.06945v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.06945

0
arXiv - CSCL

RecallM: An Adaptable Memory Mechanism with Temporal Understanding for Large Language Models. (arXiv:2307.02738v3 [cs.AI] UPDATED) 

arxiv.org/abs/2307.02738

0
arXiv - CSCL

Generalized Knowledge Distillation for Auto-regressive Language Models. (arXiv:2306.13649v2 [cs.LG] UPDATED) 

arxiv.org/abs/2306.13649

0
arXiv - CSCL

LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization. (arXiv:2306.01102v5 [cs.NE] UPDATED) 

arxiv.org/abs/2306.01102

0
arXiv - CSCL

Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts. (arXiv:2305.13300v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13300

0
arXiv - CSCL

Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources. (arXiv:2305.13269v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13269

0
arXiv - CSCL

"What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge. (arXiv:2305.12091v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12091

0
arXiv - CSCL

Cross-Modal Retrieval for Motion and Text via DopTriple Loss. (arXiv:2305.04195v3 [cs.CV] UPDATED) 

arxiv.org/abs/2305.04195

0
arXiv - CSCL

Bridging Discrete and Backpropagation: Straight-Through and Beyond. (arXiv:2304.08612v2 [cs.LG] UPDATED) 

arxiv.org/abs/2304.08612

0
arXiv - CSCL

On the Possibilities of AI-Generated Text Detection. (arXiv:2304.04736v3 [cs.CL] UPDATED) 

arxiv.org/abs/2304.04736

0
arXiv - CSCL

Chain of Hindsight Aligns Language Models with Feedback. (arXiv:2302.02676v7 [cs.LG] UPDATED) 

arxiv.org/abs/2302.02676

0
arXiv - CSCL

Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data. (arXiv:2302.00674v4 [cs.LG] UPDATED) 

arxiv.org/abs/2302.00674

0
arXiv - CSCL

Query Rewriting for Effective Misinformation Discovery. (arXiv:2210.07467v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.07467

0
arXiv - CSCL

DialoGen: Generalized Long-Range Context Representation for Dialogue Systems. (arXiv:2210.06282v4 [cs.CL] UPDATED) 

arxiv.org/abs/2210.06282

0
arXiv - CSCL

FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation. (arXiv:2210.00193v3 [cs.CL] UPDATED) 

arxiv.org/abs/2210.00193

0
arXiv - CSCL

Controlling Topic-Focus Articulation in Meaning-to-Text Generation using Graph Neural Networks. (arXiv:2310.02053v1 [cs.CL]) 

arxiv.org/abs/2310.02053

0
arXiv - CSCL

Tuning Large language model for End-to-end Speech Translation. (arXiv:2310.02050v1 [cs.CL]) 

arxiv.org/abs/2310.02050

0
arXiv - CSCL

Jury: A Comprehensive Evaluation Toolkit. (arXiv:2310.02040v1 [cs.CL]) 

arxiv.org/abs/2310.02040

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.

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy