Published October 8, 2025
| Version v1
Report
Open
Theoretical Limits of Feedback Alignment in Preference-Based Fine-Tuning of Large Language Models
Authors/Creators
Files
Bridging_the_Gap_Between_Rich_and_Sparse_Knowledge_Graphs_for_Multi_Hop_Reasoning_via_Transfer_Learning_and_Natural_Language_Techniques__Copy_.pdf
Additional details
Dates
- Submitted
-
2025
References
- Z. Gao, "Modeling reasoning as markov decision processes: A theoretical investigation into nlp transformer models," 2025.
- Y. Sang, "Towards explainable rag: Interpreting the influence of retrieved passages on generation," 2025.
- Y. Sang, "Robustness of fine-tuned llms under noisy retrieval inputs," in 2025 6th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA), pp. 417–420, IEEE, 2025.
- Z. Gao, "Theoretical limits of feedback alignment in preference-based fine-tuning of ai models," 2025.
- S. Lin, "Hybrid fuzzing with llm-guided input mutation and semantic feedback," 2025.
- S. Lin, "Llm-driven adaptive source–sink identification and false positive mitigation for static analysis," 2025.
- Z. Zhang, "Unified operator fusion for heterogeneous hardware in ml inference frameworks," 2025.
- Z. Gao, "Feedback-to-text alignment: Llm learning consistent natural language generation from user ratings and loyalty data," 2025.