Show newer
arXiv - CSCL

What does self-attention learn from Masked Language Modelling?. (arXiv:2304.07235v2 [cond-mat.dis-nn] UPDATED) 

arxiv.org/abs/2304.07235

0
arXiv - CSCL

Data Portraits: Recording Foundation Model Training Data. (arXiv:2303.03919v2 [cs.LG] UPDATED) 

arxiv.org/abs/2303.03919

0
arXiv - CSCL

Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering. (arXiv:2303.01903v3 [cs.CV] UPDATED) 

arxiv.org/abs/2303.01903

0
arXiv - CSCL

Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Types. (arXiv:2302.01313v7 [cs.LG] UPDATED) 

arxiv.org/abs/2302.01313

0
arXiv - CSCL

Controllable Citation Sentence Generation with Language Models. (arXiv:2211.07066v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.07066

0
arXiv - CSCL

Beyond Grounding: Extracting Fine-Grained Event Hierarchies Across Modalities. (arXiv:2206.07207v2 [cs.CV] UPDATED) 

arxiv.org/abs/2206.07207

0
arXiv - CSCL

A Cognitive Architecture for Machine Consciousness and Artificial Superintelligence: Thought Is Structured by the Iterative Updating of Working Memory. (arXiv:2203.17255v6 [q-bio.NC] UPDATED) 

arxiv.org/abs/2203.17255

0
arXiv - CSCL

AmbiFC: Fact-Checking Ambiguous Claims with Evidence. (arXiv:2104.00640v4 [cs.CL] UPDATED) 

arxiv.org/abs/2104.00640

0
arXiv - CSCL

Learning From How Humans Correct. (arXiv:2102.00225v18 [cs.CL] UPDATED) 

arxiv.org/abs/2102.00225

0
arXiv - CSCL

ComOM at VLSP 2023: A Dual-Stage Framework with BERTology and Unified Multi-Task Instruction Tuning Model for Vietnamese Comparative Opinion Mining. (arXiv:2312.09000v1 [cs.CL]) 

arxiv.org/abs/2312.09000

0
arXiv - CSCL

FrameFinder: Explorative Multi-Perspective Framing Extraction from News Headlines. (arXiv:2312.08995v1 [cs.IR]) 

arxiv.org/abs/2312.08995

0
arXiv - CSCL

Detecting value-expressive text posts in Russian social media. (arXiv:2312.08968v1 [cs.CL]) 

arxiv.org/abs/2312.08968

0
arXiv - CSCL

Math-Shepherd: A Label-Free Step-by-Step Verifier for LLMs in Mathematical Reasoning. (arXiv:2312.08935v1 [cs.AI]) 

arxiv.org/abs/2312.08935

0
arXiv - CSCL

Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent. (arXiv:2312.08926v1 [cs.AI]) 

arxiv.org/abs/2312.08926

0
arXiv - CSCL

Using eye tracking to investigate what native Chinese speakers notice about linguistic landscape images. (arXiv:2312.08906v1 [cs.CL]) 

arxiv.org/abs/2312.08906

0
arXiv - CSCL

Boosting LLM Reasoning: Push the Limits of Few-shot Learning with Reinforced In-Context Pruning. (arXiv:2312.08901v1 [cs.CL]) 

arxiv.org/abs/2312.08901

0
arXiv - CSCL

Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning. (arXiv:2312.08865v1 [cs.CV]) 

arxiv.org/abs/2312.08865

0
arXiv - CSCL

TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-training. (arXiv:2312.08846v1 [cs.LG]) 

arxiv.org/abs/2312.08846

0
arXiv - CSCL

Evaluating Large Language Models for Health-related Queries with Presuppositions. (arXiv:2312.08800v1 [cs.CL]) 

arxiv.org/abs/2312.08800

0
arXiv - CSCL

Forbidden Facts: An Investigation of Competing Objectives in Llama-2. (arXiv:2312.08793v1 [cs.LG]) 

arxiv.org/abs/2312.08793

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