paper-with-me

Papers

Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning

2024-03-30 · Nick Mecklenburg, Yiyou Lin, Xiaoxiao Li, Daniel Holstein, Leonardo Nunes, Sara Malvar, Bruno Silva, Ranveer Chandra, Vijay Aski, Pavan Kumar Reddy Yannam, Tolga Aktas, Todd Hendry

In recent years, Large Language Models (LLMs) have shown remarkable performance in generating human-like text, proving to be a valuable asset across various applications. However, adapting these models to incorporate new, out-of-domain knowledge remains a challenge, particularly for facts and events that occur after the model's knowledge cutoff date. This paper investigates the effectiveness of Supervised Fine-Tuning (SFT) as a method for knowledge injection in LLMs, specifically focusing on the domain of recent sporting events. We compare different dataset generation strategies -- token-based and fact-based scaling -- to create training data that helps the model learn new information. Our experiments on GPT-4 demonstrate that while token-based scaling can lead to improvements in Q&A accuracy, it may not provide uniform coverage of new knowledge. Fact-based scaling, on the other hand, offers a more systematic approach to ensure even coverage across all facts. We present a novel dataset generation process that leads to more effective knowledge ingestion through SFT, and our results show considerable performance improvements in Q&A tasks related to out-of-domain knowledge. This study contributes to the understanding of domain adaptation for LLMs and highlights the potential of SFT in enhancing the factuality of LLM responses in specific knowledge domains.

📄 PDF Abstract BibTeX arXiv:2404.00213

Code (0)

등록된 구현이 없습니다.

Tasks

Dataset GenerationDomain Adaptation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Knowledge Prompts: Injecting World Knowledge into Language Models through Soft Prompts

2022-10-10 · Cicero Nogueira dos santos, Zhe Dong, Daniel Cer, John Nham 외

Soft prompts have been recently proposed as a tool for adapting large frozen language models (LMs) to new tasks. In this work, we repurpose soft prompts to the task of injecting world knowledge into LMs. We introduce a m…

Self-Supervised LearningWorld Knowledge

Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text

2019-11-13 · WS 2019 11 · Ian Porada, Kaheer Suleman, Jackie Chi Kit Cheung

Modeling semantic plausibility requires commonsense knowledge about the world and has been used as a testbed for exploring various knowledge representations. Previous work has focused specifically on modeling physical pl…

Natural Language Understanding

Improving Unsupervised Commonsense Reasoning Using Knowledge-Enabled Natural Language Inference

2021-11-01 · Findings (EMNLP) 2021 11 · Canming Huang, Weinan He, Yongmei Liu

Recent methods based on pre-trained language models have shown strong supervised performance on commonsense reasoning. However, they rely on expensive data annotation and time-consuming training. Thus, we focus on unsupe…

Natural Language InferenceTransfer LearningWinowhy

GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method

2020-10-23 · Nicole Peinelt, Marek Rei, Maria Liakata

Large pre-trained language models such as BERT have been the driving force behind recent improvements across many NLP tasks. However, BERT is only trained to predict missing words - either behind masks or in the next sen…

Semantic SimilaritySemantic Textual SimilaritySentenceUnsupervised Pre-training+1

CoLAKE: Contextualized Language and Knowledge Embedding

2020-10-01 · COLING 2020 8 · Tianxiang Sun, Yunfan Shao, Xipeng Qiu, Qipeng Guo 외

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the per…

Entity EmbeddingsKnowledge Graph CompletionKnowledge Probing