paper-with-me

Papers

Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in QA Agents

2025-02-26 · Ashley Lewis, Michael White, Jing Liu, Toshiaki Koike-Akino, Kieran Parsons, Ye Wang

The deployment of Large Language Models (LLMs) in customer support is constrained by hallucination-generating false information-and the high cost of proprietary models. To address these challenges, we propose a retrieval-augmented question-answering (QA) pipeline and explore how to balance human input and automation. Using a dataset of questions about a Samsung Smart TV user manual, we demonstrate that synthetic data generated by LLMs outperforms crowdsourced data in reducing hallucination in finetuned models. We also compare self-training (fine-tuning models on their own outputs) and knowledge distillation (fine-tuning on stronger models' outputs, e.g., GPT-4o), and find that self-training achieves comparable hallucination reduction. We conjecture that this surprising finding can be attributed to increased exposure bias issues in the knowledge distillation case and support this conjecture with post hoc analysis. We also improve robustness to unanswerable questions and retrieval failures with contextualized "I don't know" responses. These findings show that scalable, cost-efficient QA systems can be built using synthetic data and self-training with open-source models, reducing reliance on proprietary tools or costly human annotations.

📄 PDF Abstract BibTeX arXiv:2502.19545

Code (0)

등록된 구현이 없습니다.

Tasks

HallucinationKnowledge DistillationQuestion AnsweringRetrieval

Methods 이 논문이 사용한 방법론

customer support 설명 없음
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
HOC 설명 없음

Similar Papers 제목 키워드 기반

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation

2022-12-19 · Chandra Bhagavatula, Jena D. Hwang, Doug Downey, Ronan Le Bras 외

Commonsense capabilities of pre-trained language models dramatically improve with scale, leading many to believe that scale is the only winning recipe. But is it? Here, we investigate an alternative that a priori seems i…

Imitation LearningKnowledge Distillation

Knowledge Distillation as Self-Supervised Learning

2022-01-17 · ICLR Track Blog 2022 5 · Anonymous

Self-supervised learning (SSL) methods have been shown to effectively train large neural networks with unlabeled data. These networks can produce useful image representations that can exceed the performance of supervised…

Knowledge DistillationSelf-Supervised Learning

A New Training Framework for Deep Neural Network

2021-03-12 · Zhenyan Hou, Wenxuan Fan

Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance c…

Knowledge Distillation

On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals

2021-07-30 · Haizhou Shi, Youcai Zhang, Siliang Tang, Wenjie Zhu 외

It is a consensus that small models perform quite poorly under the paradigm of self-supervised contrastive learning. Existing methods usually adopt a large off-the-shelf model to transfer knowledge to the small one via d…

ClusteringContrastive LearningKnowledge Distillation

SIKeD: Self-guided Iterative Knowledge Distillation for mathematical reasoning

2024-10-24 · Shivam Adarsh, Kumar Shridhar, Caglar Gulcehre, Nicholas Monath 외

Large Language Models (LLMs) can transfer their reasoning skills to smaller models by teaching them to generate the intermediate reasoning process required to solve multistep reasoning tasks. While LLMs can accurately so…

Knowledge DistillationMathematical Reasoning