Papers by Demin Song

6 papers
Code Needs Comments: Enhancing Code LLMs with Comment Augmentation (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) require a deep understanding of programming languages and their correlation with natural languages (NLs).
Approach: They propose a data augmentation method that generates comments for existing code and a filtering strategy that filters out code data poorly correlated with natural language.
Outcome: The proposed method outperforms the model trained on the augmented data and the model further trained on data without augmentation on two widely-used programming skill benchmarks.
UnitCoder: Scalable Code Synthesis from Pre-training Corpora (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel at code understanding and generation, yet code generation remains a challenge.
Approach: They propose a model that supervises pre-training data quality through automatically generated unit tests while ensuring correctness via an iterative fix and refine flow.
Outcome: The proposed model improves performance on a large dataset with high quality pre-training data.
Text Adversarial Purification as Defense against Adversarial Attacks (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for defending against adversarial examples are difficult due to the discrete nature of texts.
Approach: They propose a novel adversarial purification method that aims to remove adversarials and make correct predictions based on the recovered clean samples.
Outcome: The proposed method can defend against word-substitution adversarial attacks using language models.
CritiQ: Mining Data Quality Criteria from Human Preferences (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to train language models rely on manual design, perplexity, or careful prompt engineering.
Approach: They propose a method that automatically mines criteria from human preferences for data quality with only 30 human-annotated pairs and performs efficient data selection.
Outcome: The proposed method improves on human-annotated test sets and shows high accuracy on code, math, and logic domains.
Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning (2021.emnlp-main)

Copied to clipboard

Challenge: Pre-trained models can be maliciously poisoned with certain triggers, causing a security threat.
Approach: They propose a stronger weight poisoning attack method that introduces a layerwise weight poison strategy to plant deeper backdoors.
Outcome: The proposed method can be widely applied and provide hints for future models robustness studies.
Case2Code: Scalable Synthetic Data for Code Generation (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown outstanding breakthroughs in code generation.
Approach: They propose a case-to-code induction task that exploits the expressiveness and correctness of programs by incorporating LLMs into their training.
Outcome: The proposed task improves distribution case-to-code induction and various coding generation tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations