Show newer
arXiv - CSCL

How FaR Are Large Language Models From Agents with Theory-of-Mind?. (arXiv:2310.03051v1 [cs.CL]) 

arxiv.org/abs/2310.03051

0
arXiv - CSCL

How Prevalent is Gender Bias in ChatGPT? -- Exploring German and English ChatGPT Responses. (arXiv:2310.03031v1 [cs.CL]) 

arxiv.org/abs/2310.03031

0
arXiv - CSCL

Named Entity Inclusion in Abstractive Text Summarization. (arXiv:2307.02570v1 [cs.CL] CROSS LISTED) 

arxiv.org/abs/2307.02570

0
arXiv - CSCL

Who's Harry Potter? Approximate Unlearning in LLMs. (arXiv:2310.02238v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.02238

0
arXiv - CSCL

OceanGPT: A Large Language Model for Ocean Science Tasks. (arXiv:2310.02031v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.02031

0
arXiv - CSCL

Effective and Parameter-Efficient Reusing Fine-Tuned Models. (arXiv:2310.01886v2 [cs.LG] UPDATED) 

arxiv.org/abs/2310.01886

0
arXiv - CSCL

Preserving Phonemic Distinctions for Ordinal Regression: A Novel Loss Function for Automatic Pronunciation Assessment. (arXiv:2310.01839v2 [eess.AS] UPDATED) 

arxiv.org/abs/2310.01839

0
arXiv - CSCL

LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples. (arXiv:2310.01469v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.01469

0
arXiv - CSCL

The Entity-Deduction Arena: A playground for probing the conversational reasoning and planning capabilities of LLMs. (arXiv:2310.01468v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.01468

0
arXiv - CSCL

Fewer is More: Trojan Attacks on Parameter-Efficient Fine-Tuning. (arXiv:2310.00648v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.00648

0
arXiv - CSCL

ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving. (arXiv:2309.17452v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.17452

0
arXiv - CSCL

DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models. (arXiv:2309.14509v2 [cs.LG] UPDATED) 

arxiv.org/abs/2309.14509

0
arXiv - CSCL

Investigating the Catastrophic Forgetting in Multimodal Large Language Models. (arXiv:2309.10313v3 [cs.CL] UPDATED) 

arxiv.org/abs/2309.10313

0
arXiv - CSCL

Sparse Autoencoders Find Highly Interpretable Features in Language Models. (arXiv:2309.08600v3 [cs.LG] UPDATED) 

arxiv.org/abs/2309.08600

0
arXiv - CSCL

Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness. (arXiv:2308.16175v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.16175

0
arXiv - CSCL

Instruction Tuning for Large Language Models: A Survey. (arXiv:2308.10792v3 [cs.CL] UPDATED) 

arxiv.org/abs/2308.10792

0
arXiv - CSCL

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. (arXiv:2308.08155v2 [cs.AI] UPDATED) 

arxiv.org/abs/2308.08155

0
arXiv - CSCL

L-Eval: Instituting Standardized Evaluation for Long Context Language Models. (arXiv:2307.11088v3 [cs.CL] UPDATED) 

arxiv.org/abs/2307.11088

0
arXiv - CSCL

FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets. (arXiv:2307.10928v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.10928

0
arXiv - CSCL

ValiTex -- a unified validation framework for computational text-based measures of social science constructs. (arXiv:2307.02863v4 [cs.CL] UPDATED) 

arxiv.org/abs/2307.02863

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