Papers by Bach Le
Continual Safety Alignment via Gradient-Based Sample Selection (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models require continuous adaptation to new domains, tasks, and evolving requirements. |
| Approach: | They propose a gradient-based sample selection method that filters high-gradient samples during fine-tuning. |
| Outcome: | The proposed method significantly improves alignment preservation while maintaining competitive task performance on continual domain tasks. |
CodeWiki: Evaluating AI’s Ability to Generate Holistic Documentation for Large-Scale Codebases (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing automated methods struggle to capture rich semantic dependencies and architectural structure. |
| Approach: | They propose a framework for automated repository-level documentation across seven programming languages. |
| Outcome: | The proposed framework outperforms the closed-source DeepWiki benchmark by 68.79% and is open source to support future research. |
Can LLMs Reason About Program Semantics? A Comprehensive Evaluation of LLMs on Formal Specification Inference (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly being used to automate programming tasks. |
| Approach: | They propose a benchmark to evaluate LLMs' reasoning abilities on program semantics. |
| Outcome: | The proposed benchmark shows that LLMs perform well with simple control flows but struggle with more complex structures, especially loops, even with advanced prompting. |