When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets
- Aladin Djuhera
- Farhan Ahmed
- et al.
- 2026
- ICLR 2026
Conference paper
Publications
13 results for Farhan Ahmed
LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics
- Farhan Ahmed
- Yuya Ong
- et al.
- 2026
- ICLR 2026
Workshop paperTSR: Trajectory‑Search Rollouts for Multi‑Turn RL of LLM Agents
- Aladin Djuhera
- Swanand Ravindra Kadhe
- et al.
- 2026
- ICLR 2026
Workshop paperSafeCOMM: A Study on Safety Degradation in Fine-Tuned Telecom Large Language Models
- Aladin Djuhera
- Swanand Ravindra Kadhe
- et al.
- 2026
- WCNC 2026
Conference paperFixing It in Post: A Comparative Study of LLM Post-Training Data Quality and Model Performance
- Aladin Djuhera
- Swanand Ravindra Kadhe
- et al.
- 2025
- NeurIPS 2025
Conference paperMermaidSeqBench: An Evaluation Benchmark for LLM-to-Mermaid Sequence Diagram Generation
- Basel Shbita
- Farhan Ahmed
- et al.
- 2025
- NeurIPS 2025
Workshop paperWhen Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets
- Aladin Djuhera
- Farhan Ahmed
- et al.
- 2025
- NeurIPS 2025
Workshop paperSafeCOMM: Investigating Safety Degradation in Fine-Tuned Telecom Large Language Models
- Aladin Djuhera
- Swanand Ravindra Kadhe
- et al.
- 2025
- NeurIPS 2025
Workshop paperSafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
- Aladin Djuhera
- Swanand Ravindra Kadhe
- et al.
- 2025
- ICLR 2025
Workshop paperSplit, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
- Swanand Ravindra Kadhe
- Farhan Ahmed
- et al.
- 2024
- ICML 2024
Workshop paper