LLMs Learn Better In-Context from Rules than from Examples
Paper • 2609.03213 • Published
CIFT
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
yukyung
authored 3
papers 17 days ago
yukyung
authored a
paper about 2 months ago
yukyung
authored 11
papers 4 months ago
Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning
Paper • 2606.25524 • Published • 2
Painsight: An Extendable Opinion Mining Framework for Detecting Pain Points Based on Online Customer Reviews
Paper • 2306.02043 • Published
Multi$^2$OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT
Paper • 2009.08128 • Published
RAPID: Training-free Retrieval-based Log Anomaly Detection with PLM considering Token-level information
Paper • 2311.05160 • Published
A Gradient Accumulation Method for Dense Retriever under Memory Constraint
Paper • 2406.12356 • Published
Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streams
Paper • 2603.19250 • Published
LAnoBERT: System Log Anomaly Detection based on BERT Masked Language Model
Paper • 2111.09564 • Published
CheckEval: Robust Evaluation Framework using Large Language Model via Checklist
Paper • 2403.18771 • Published
RExBench: Can coding agents autonomously implement AI research extensions?
Paper • 2506.22598 • Published • 11
Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models
Paper • 2404.13919 • Published
CIRF: Tokenizing Chain-of-Thoughts into Reusable Functional Units for Efficient Latent Reasoning in Large Language Models
Paper • 2605.28292 • Published
junhmm
updated a
model 5 months ago
junhmm
published a
model 5 months ago
junhmm
updated a
model 5 months ago
junhmm
published a
model 5 months ago
junhmm
updated a
model 5 months ago