Show newer
arXiv - CSCL

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model. (arXiv:2306.03341v5 [cs.LG] UPDATED) 

arxiv.org/abs/2306.03341

0
arXiv - CSCL

Handling Realistic Label Noise in BERT Text Classification. (arXiv:2305.16337v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.16337

0
arXiv - CSCL

Language Model Tokenizers Introduce Unfairness Between Languages. (arXiv:2305.15425v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.15425

0
arXiv - CSCL

Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples. (arXiv:2305.15269v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.15269

0
arXiv - CSCL

Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM. (arXiv:2305.15255v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.15255

0
arXiv - CSCL

A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis. (arXiv:2305.15054v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.15054

0
arXiv - CSCL

CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering. (arXiv:2305.14869v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14869

0
arXiv - CSCL

Getting MoRE out of Mixture of Language Model Reasoning Experts. (arXiv:2305.14628v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14628

0
arXiv - CSCL

Learning Semantic Role Labeling from Compatible Label Sequences. (arXiv:2305.14600v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14600

0
arXiv - CSCL

Query Rewriting for Retrieval-Augmented Large Language Models. (arXiv:2305.14283v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14283

0
arXiv - CSCL

Question Answering as Programming for Solving Time-Sensitive Questions. (arXiv:2305.14221v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14221

0
arXiv - CSCL

Enhancing Black-Box Few-Shot Text Classification with Prompt-Based Data Augmentation. (arXiv:2305.13785v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13785

0
arXiv - CSCL

PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training. (arXiv:2305.13723v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13723

0
arXiv - CSCL

Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning. (arXiv:2305.13660v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13660

0
arXiv - CSCL

ReSee: Responding through Seeing Fine-grained Visual Knowledge in Open-domain Dialogue. (arXiv:2305.13602v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13602

0
arXiv - CSCL

BioDEX: Large-Scale Biomedical Adverse Drug Event Extraction for Real-World Pharmacovigilance. (arXiv:2305.13395v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13395

0
arXiv - CSCL

Can LLMs facilitate interpretation of pre-trained language models?. (arXiv:2305.13386v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13386

0
arXiv - CSCL

Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents. (arXiv:2305.13303v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13303

0
arXiv - CSCL

SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives. (arXiv:2305.13192v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13192

0
arXiv - CSCL

SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables. (arXiv:2305.13186v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13186

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