Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
Paper • 2402.18540 • Published
Haoyu Zhao
zzzzzhy
AI & ML interests
None yet
Recent Activity
authored a paper about 13 hours ago
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt
Templates authored a paper about 13 hours ago
Can Models Learn Skill Composition from Examples? authored a paper about 13 hours ago
Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data
Synthesis and Self-CorrectionOrganizations
authored 9
papers about 13 hours ago
Can Models Learn Skill Composition from Examples?
Paper • 2409.19808 • Published • 9
Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
Paper • 2508.03613 • Published • 16
Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving on Inequalities
Paper • 2505.12680 • Published
AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
Paper • 2507.15887 • Published
Contextual Drag: How Errors in the Context Affect LLM Reasoning
Paper • 2602.04288 • Published • 2
Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification
Paper • 2603.19329 • Published • 1
AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms
Paper • 2602.09464 • Published
Task-Specific Skill Localization in Fine-tuned Language Models
Paper • 2302.06600 • Published
updated a
dataset 4 days ago
published a
dataset 4 days ago
updated a
dataset 9 months ago
updated 2
models 10 months ago
Lean version
1
#2 opened 11 months ago
by 
desaxce
Update README.md
#1 opened 11 months ago
by 
kaiyuy
Update README.md
1
#1 opened 11 months ago
by kaiyuy
published a
model 11 months ago
updated a
dataset 11 months ago
liked a
dataset about 1 year ago