Papers with distillation framework

11 papers
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.
Topic-Regularized Authorship Representation Learning (2022.emnlp-main)

Copied to clipboard

Challenge: Existing techniques for authorship attribution have focused on out-of-distribution in topics or authors.
Approach: They propose a framework that creates authorship representation with reduced reliance on topic-specific information to handle a large number of unseen authors and topics.
Outcome: The proposed framework has improved over baselines in 4 out of 6 cases.
CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning (2024.acl-long)

Copied to clipboard

Challenge: Existing approaches to generalize commonsense reasoning lack instantiated knowledge and require pre-built concept taxonomies and annotations.
Approach: They propose a framework that iteratively performs contextualized conceptualization and instantiation over commonsense knowledge bases by instructing large language models to generate both types of knowledge with critic filtering.
Outcome: Empirical results show that distilling CANDLE on student models provides benefits across three downstream tasks.
uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes (2025.naacl-long)

Copied to clipboard

Challenge: Recent work on distilling Whisper’s knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50%.
Approach: They propose a framework that distills Whisper’s knowledge into small models using pseudo-labels and reduces the size by up to 50%.
Outcome: The proposed model outperforms the teacher model by 5-7 WER points and is 25-50% more efficient when scaling the data.
MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for acquiring large-scale intentions generate product-centric intentions without product images and incur high costs for scalability.
Approach: They propose a multimodal framework that allows Large Vision-Language Models to infer purchase intentions from multimodal product metadata and prioritize human-centric ones.
Outcome: The proposed framework shows that it is robust to different prompts and superior to previous methods.
ConGen: Unsupervised Control and Generalization Distillation For Sentence Representation (2022.findings-emnlp)

Copied to clipboard

Challenge: Sentence representations are essential in many NLP tasks operating at the sentence level.
Approach: They propose an unsupervised sentence representation method to reduce the supervised-unsupervised performance gap for smaller models.
Outcome: The proposed method outperforms supervised training on STS, text classification, and natural language inference tasks on smaller models.
AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to distilling large language models (LLMs) are inefficient and generate excessively long chain-of-thought reasoning even for inputs that admit concise solutions.
Approach: They propose a distillation framework that empowers non-reasoning LLMs to think only when necessary.
Outcome: The proposed framework reduces reasoning length up to 71% with minimal accuracy loss while preserving accuracy.
Experience is the Teacher: Reusing Atomic Thoughts from LLMs to Improve Medical Dialogue (2026.findings-acl)

Copied to clipboard

Challenge: Recent large reasoning models (LLMs) lack dynamic and diverse thinking capabilities . reusing atomic thoughts provides a practical pathway toward dynamic reasoning .
Approach: They propose a framework that extracts atomic thoughts from teacher models and reuses them to guide reasoning and generate responses.
Outcome: The proposed framework extracts atomic thoughts from teacher models and reuses them to guide reasoning and generate responses.
Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models (2025.emnlp-main)

Copied to clipboard

Challenge: Recent efforts to develop lightweight and practical sentiment analysis models are limited by manual instruction and large-scale user texts.
Approach: They propose a framework for sentiment analysis that uses attribute-based instruction construction and difficulty-based data filtering to distill knowledge.
Outcome: The proposed framework outperforms baseline methods in data efficiency and performance.
Probe Then Retrieve and Reason: Distilling Probing and Reasoning Capabilities into Smaller Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Recent research efforts have focused on distilling Large Language Models into Small Language Model (SLMs) however, the results of CoT distillation are inadequate for knowledge-intensive reasoning tasks.
Approach: They propose a retrieval-based framework which distills question probing and reasoning capabilities from Large Language Models into SLMs.
Outcome: The proposed framework improves probing and reasoning capabilities of large language models in knowledge-intensive reasoning tasks.
Do LLMs Encode Functional Importance of Reasoning Tokens ? (2026.acl-long)

Copied to clipboard

Challenge: Existing compact reasoning approaches generate long reasoning chains, but they lack a mechanism to encode token-level functional importance for answer generation.
Approach: They propose a procedure that iteratively removes reasoning tokens from models and prunes them to yield length-controlled reasoning chains.
Outcome: The proposed procedure outperforms a frontier model at reasoning lengths and shows that attention scores predict greedy pruning ranks.

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