Papers with DISCO
FaithfulPersona: Balancing Faithfulness and Personalization in Code Explanations through Self-Critique (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for generating faithful code explanations face challenges balancing faithfulness to the original code and personalization for diverse user needs. |
| Approach: | They propose a benchmark and method for generating faithful personalized code explanations using code samples and user profiles. |
| Outcome: | The proposed method achieves 3.7% improvement in Pass@5 compared to the strong baseline method, Self-Consistency, while maintaining high personalization with a 61.08% win rate in the LLM-as-a-Judge evaluation. |
DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data (2025.findings-emnlp)
Copied to clipboard
Yuhang Zhou, Jing Zhu, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang
| Challenge: | Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). |
| Approach: | a new study proposes a domain-informed self-consistency policy optimization extension to GRPO that addresses inter-group imbalance. |
| Outcome: | a new extension of GRPO addresses inter-group imbalance with two key innovations . the proposed method outperforms existing GR PO variants by 5% on Qwen3 models . |
DISCO: Distilling Counterfactuals with Large Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | high-quality counterfactual data is scarce for most tasks and not easily generated at scale. |
| Approach: | They propose a method for automatically generating high-quality counterfactual data at scale . they use a large general language model to generate phrasal perturbations and filter them . |
| Outcome: | The proposed method is task-agnostic and can be applied to the task of natural language inference. |
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts (2022.acl-long)
Copied to clipboard
| Challenge: | Existing models that focus on identifying functional (dis)similarity of source code get confused when trying to identify functional (Dis)-similarities. |
| Approach: | They propose to pre-train a Transformer model with such automatically generated program contrasts to better identify similar code in the wild and differentiate vulnerable programs from benign ones. |
| Outcome: | The proposed model outperforms existing models in vulnerability and code clone detection tasks even with much less data. |
Outdated Issue Aware Decoding for Factual Knowledge Editing (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge editing methods retain outdated responses for reasoning questions . naively retraining LLMs can be computationally intensive and can lead to catastrophic forgetting . |
| Approach: | They propose a simple yet effective decoding strategy to enhance edited models on reasoning questions. |
| Outcome: | The proposed method outDates ISsue aware deCOding (DISCO) to improve models on reasoning questions. |