Show newer
arXiv - CSCL

Chain of Code: Reasoning with a Language Model-Augmented Code Emulator. (arXiv:2312.04474v2 [cs.CL] UPDATED) 

arxiv.org/abs/2312.04474

0
arXiv - CSCL

Beyond Surface: Probing LLaMA Across Scales and Layers. (arXiv:2312.04333v2 [cs.CL] UPDATED) 

arxiv.org/abs/2312.04333

0
arXiv - CSCL

Methods to Estimate Large Language Model Confidence. (arXiv:2312.03733v2 [cs.CL] UPDATED) 

arxiv.org/abs/2312.03733

0
arXiv - CSCL

Exploring the Robustness of Model-Graded Evaluations and Automated Interpretability. (arXiv:2312.03721v2 [cs.CL] UPDATED) 

arxiv.org/abs/2312.03721

0
arXiv - CSCL

SymNoise: Advancing Language Model Fine-tuning with Symmetric Noise. (arXiv:2312.01523v2 [cs.CL] UPDATED) 

arxiv.org/abs/2312.01523

0
arXiv - CSCL

Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges. (arXiv:2311.15766v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.15766

0
arXiv - CSCL

\'UFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution. (arXiv:2311.14391v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.14391

0
arXiv - CSCL

LM-Cocktail: Resilient Tuning of Language Models via Model Merging. (arXiv:2311.13534v4 [cs.CL] UPDATED) 

arxiv.org/abs/2311.13534

0
arXiv - CSCL

The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4. (arXiv:2311.07361v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.07361

0
arXiv - CSCL

Quality-Diversity through AI Feedback. (arXiv:2310.13032v4 [cs.CL] UPDATED) 

arxiv.org/abs/2310.13032

0
arXiv - CSCL

Measuring Pointwise $\mathcal{V}$-Usable Information In-Context-ly. (arXiv:2310.12300v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12300

0
arXiv - CSCL

DialogueLLM: Context and Emotion Knowledge-Tuned LLaMA Models for Emotion Recognition in Conversations. (arXiv:2310.11374v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.11374

0
arXiv - CSCL

Conversational Health Agents: A Personalized LLM-Powered Agent Framework. (arXiv:2310.02374v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.02374

0
arXiv - CSCL

Spider4SPARQL: A Complex Benchmark for Evaluating Knowledge Graph Question Answering Systems. (arXiv:2309.16248v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.16248

0
arXiv - CSCL

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM. (arXiv:2309.14348v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.14348

0
arXiv - CSCL

Goal-Oriented Prompt Attack and Safety Evaluation for LLMs. (arXiv:2309.11830v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.11830

0
arXiv - CSCL

FIND: A Function Description Benchmark for Evaluating Interpretability Methods. (arXiv:2309.03886v3 [cs.CL] UPDATED) 

arxiv.org/abs/2309.03886

0
arXiv - CSCL

On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook. (arXiv:2307.16680v5 [cs.LG] UPDATED) 

arxiv.org/abs/2307.16680

0
arXiv - CSCL

Max-Margin Token Selection in Attention Mechanism. (arXiv:2306.13596v4 [cs.LG] UPDATED) 

arxiv.org/abs/2306.13596

0
arXiv - CSCL

Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark. (arXiv:2305.14938v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14938

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