12 papers
Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking
Tien Nam Nguyen, Emanuela Boros, Ahmed Hamdi +3
Large language models (LLMs) have recently shown promise for historical entity linking, but preference optimization for this task is often formulated with only one negative candida…
On Behavioral Alignment of Model-Code and Human-Code Understandability via Behavioral Proxies
Xiaokai Rong, Aashish Yadavally, Anh H. N. Nguyen +2
Code understandability is a critical aspect of software quality. Prior research has largely focused on this attribute from a human-centric or code-centric perspective, while it sho…
W-RAG: Source-Aware Retrieval for Enterprise Document Generation from Heterogeneous Knowledge Bases
Hridya Dhulipala, Rajesh Ombase, Michael Wang +1
Retrieval-Augmented Generation (RAG) enables large language models to incorporate external knowledge during generation, improving factual grounding and domain adaptability. However…
Post-Hoc Attention Steering of Large Language Models for Robust Code Understanding under Obfuscation
Xiaokai Rong, Aashish Yadavally, Tien N. Nguyen
Code obfuscation is widely used in software systems and malware to conceal program logic and hinder analysis, posing significant challenges for both human developers and automated…
AdaptAgent: A Multi-agent, Domain-Guided Reasoning Framework for Code Adaptation
Xiaokai Rong, Hridya Dhulipala, Aashish Yadavally +1
Developers often need to adapt into their projects the code generated from LLMs or code snippets from online forums. However, integrating them into an existing repository remains c…
Can Perplexity Serve as a Cognitive Signal for Code Understandability?
Xiaokai Rong, Mohammadali Sefidi Esfahani, Aashish Yadavally +2
Recent work suggests that token-level perplexity from large language models can align with localized human confusion during code comprehension. This raises a natural question: can…
Teaching Code LLMs to Reason with Intermediate Formal Specifications
Minh Le-Anh, Cuong Chi Le, Tien N. Nguyen
Unlike natural-language specifications, executable formal specifications provide machine-checkable constraints for verifying, debugging, and repairing code. However, writing such s…
Benchmarking Code Improvement with Progressive, Adaptive, and Interactive Feedback
Cuong Chi Le, Aashish Yadavally, Minh Le-Anh +1
Large language models (LLMs) are typically evaluated on code generation and program repair using binary functional correctness: a generated program or patch either passes or fails…
Semantic Evolution over Populations for LLM-Guided Automated Program Repair
Cuong Chi Le, Minh Le-Anh, Cuong Duc Van +1
Large language models (LLMs) have recently shown strong potential for automated program repair (APR), particularly through iterative refinement that generates and improves candidat…
Enhancing Program Repair with Specification Guidance and Intermediate Behavioral Signals
Minh Le-Anh, Cuong Chi Le, Tien N. Nguyen
Automated Program Repair (APR) has recently benefited from large language models (LLMs). However, most LLM-based APR approaches still rely primarily on coarse-grained, end-to-end s…
Fuzzwise: Intelligent Initial Corpus Generation for Fuzzing
Hridya Dhulipala, Xiaokai Rong, Aashish Yadavally +1
In mutation-based greybox fuzzing, generating high-quality input seeds for the initial corpus is essential for effective fuzzing. Rather than conducting separate phases for generat…
Cerberus: Multi-Agent Reasoning and Coverage-Guided Exploration for Static Detection of Runtime Errors
Hridya Dhulipala, Xiaokai Rong, Tien N. Nguyen
In several software development scenarios, it is desirable to detect runtime errors and exceptions in code snippets without actual execution. A typical example is to detect runtime…