BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation (2025.coling-main)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) is a method for reducing model size while preserving performance. |
| Approach: | They propose a method to distill large language models at the logit level by transferring knowledge from a large teacher model to a smaller student model. |
| Outcome: | The proposed method outperforms supervised fine-tuning, vanilla KL loss and five other distillation methods on 13 datasets. |
Similar Papers
On the Generalization vs Fidelity Paradox in Knowledge Distillation (2025.findings-acl)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. |
| Approach: | They propose to use knowledge distillation to compress large language models into smaller ones while preserving performance. |
| Outcome: | The proposed technique improves the performance of smaller models by 10% while providing only marginal benefits for larger models. |
Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning (2024.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that fine-tuning of large language models for specific tasks can be challenging . distribution shift during fine-timing can lead to performance degradation in general task capabilities . |
| Approach: | They propose a new approach that bridges the distribution gap between task datasets and LLMs by guiding fine-tuning with a distilled dataset generated by the model itself. |
| Outcome: | The proposed approach achieves comparable or superior performance on downstream tasks compared to the vanilla approach. |
Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) is a promising solution for large language models, but their deployment remains computationally expensive. |
| Approach: | They propose a framework which iteratively balances training data within a fixed computational budget and enables the transfer of knowledge from expensive teacher LLMs to smaller student models. |
| Outcome: | The proposed framework achieves state-of-the-art performance across diverse long-tailed datasets, enhancing both the efficiency and efficacy of the distilled models. |
PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs (2024.findings-acl)
Copied to clipboard
Rongzhi Zhang, Jiaming Shen, Tianqi Liu, Haorui Wang, Zhen Qin, Feng Han, Jialu Liu, Simon Baumgartner, Michael Bendersky, Chao Zhang
| Challenge: | Knowledge distillation (KD) is a technique for transferring expertise from large teacher models to compact student models with reduced memory footprints and inference costs. |
| Approach: | They propose to transfer knowledge from large teacher models to compact student models by exploiting teacher-student capacity discrepancies to generate pseudo-preference pairs where teacher outputs are preferred over student outputs. |
| Outcome: | The proposed framework exploits teacher-student capacity discrepancy to generate pseudo-preference pairs where teacher outputs are preferred over student outputs. |
Sinkhorn Distance Minimization for Knowledge Distillation (2024.lrec-main)
Copied to clipboard
Xiao Cui, Yulei Qin, Yuting Gao, Enwei Zhang, Zihan Xu, Tong Wu, Ke Li, Xing Sun, Wengang Zhou, Houqiang Li
| Challenge: | Existing knowledge distillation methods investigate divergence measures but fail to deliver effective supervision when few distribution overlap exists between teacher and student. |
| Approach: | They propose a knowledge distillation method that exploits the Sinkhorn distance to ensure a nuanced assessment of the disparity between teacher and student distributions. |
| Outcome: | The proposed method outperforms state-of-the-art methods on all kinds of LLMs with encoder-only, encoder decoder, and decoded architectures. |
Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation (2025.acl-long)
Copied to clipboard
Guoqiang Gong, Jiaxing Wang, Jin Xu, Deping Xiang, Zicheng Zhang, Leqi Shen, Yifeng Zhang, JunhuaShu JunhuaShu, ZhaolongXing ZhaolongXing, Zhen Chen, Pengzhang Liu, Ke Zhang
| Challenge: | Knowledge distillation (KD) compresses large language models into lightweight versions called student models. |
| Approach: | They propose to align the entire feature dynamics between teacher and student models by using two additional loss terms to achieve this. |
| Outcome: | The proposed method matches the entire feature dynamics between teacher and student models rather than just the final states. |
BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have revolutionized various domains with their remarkable capabilities, but their massive parameter sizes pose significant challenges for fine-tuning and inference. |
| Approach: | They propose a Bayesian Knowledge Distillation framework for compact Large Language Models in resource-constrained fine-tuning scenarios that employs Logits Dual-Scaling, Knowledge Alignment Module, and Bayes Distillations Optimization. |
| Outcome: | The proposed framework outperforms baseline methods on various state-of-the-art LLMs, including LLaMA, Qwen2, Bloom, and Vicuna. |
Flipping Knowledge Distillation: Leveraging Small Models’ Expertise to Enhance LLMs in Text Matching (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in acquiring diverse knowledge, making them highly effective across a wide range of tasks. |
| Approach: | They propose a flipped knowledge distillation paradigm where LLM learns from SLM . they propose to reinterpret LLMs as encoder-decoder models using LoRA . |
| Outcome: | The proposed model has been deployed in an online application environment and validated on financial and healthcare benchmarks and real-world applications. |
Dual-Space Knowledge Distillation for Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing large language models (LLMs) have strong generalization abilities due to their huge model capacities. |
| Approach: | They propose a dual-space knowledge distillation framework that unifies the output spaces of the two models for KD. |
| Outcome: | The proposed framework outperforms existing white-box KD frameworks on task-agnostic instruction-following benchmarks and can automatically align representations of two models with different vocabularies. |
Quantification of Large Language Model Distillation (2025.acl-long)
Copied to clipboard
Sunbowen Lee, Junting Zhou, Chang Ao, Kaige Li, Xeron Du, Sirui He, Haihong Wu, Tianci Liu, Jiaheng Liu, Hamid Alinejad-Rokny, Min Yang, Yitao Liang, Zhoufutu Wen, Shiwen Ni
| Challenge: | Existing studies have revealed the robustness degra-dation caused by data distillation. |
| Approach: | They propose a framework to evaluate and quantify model distillation . they aim to identify identity cognition contradictions and analyse multi-granularity response similarities across models to measure the extent of homogenization. |
| Outcome: | The proposed framework addresses two key aspects: (1) Identifying identity cognition contradictions to assess discrepancies in how models perceive and represent identity-related information; (2) Analyzing multi-granularity response similarities across models to measure the extent of homogenization. |