Unsupervised Text Representation Learning via Instruction-Tuning for Zero-Shot Dense Retrieval
Dense retrieval systems are commonly used for information retrieval (IR). They rely on learning text representations through an encoder and usually require supervised modeling via labelled data which can be costly to obtain or simply unavailable. In this study, we introduce a novel unsupervised text representation learning technique via instruction-tuning the pre-trained encoder-decoder large language models (LLM) under the dual-encoder retrieval framework. We demonstrate the corpus representation can be augmented by the representations of relevant synthetic queries generated by the instruct-tuned LLM founded on the Rao-Blackwell theorem. Furthermore, we effectively align the query and corpus text representation with self-instructed-tuning. Specifically, we first prompt an open-box pre-trained LLM to follow defined instructions (i.e. question generation and keyword summarization) to generate synthetic queries. Next, we fine-tune the pre-trained LLM with defined instructions and the generated queries that passed quality check. Finally, we generate synthetic queries with the instruction-tuned LLM for each corpora and represent each corpora by weighted averaging the synthetic queries and original corpora embeddings. We evaluate our proposed method under low-resource settings on three English and one German retrieval datasets measuring NDCG@10, MRR@100, Recall@100. We significantly improve the average zero-shot retrieval performance on all metrics, increasing open-box FLAN-T5 model variations by [3.34%, 3.50%] in absolute and exceeding three competitive dense retrievers (i.e. mDPR, T-Systems, mBART-Large), with model of size at least 38% smaller, by 1.96%, 4.62%, 9.52% absolute on NDCG@10.
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalQuestion GenerationQuestion-GenerationRepresentation LearningRetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Does Instruction Tuning Make LLMs More Consistent?
The purpose of instruction tuning is enabling zero-shot performance, but instruction tuning has also been shown to improve chain-of-thought reasoning and value alignment (Si et al., 2023). Here we consider the impact on …
SensitivityAzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning
Extending large language models (LLMs) to the speech domain has recently gained significant attention. A typical approach connects a pretrained LLM with an audio encoder through a projection module and trains the resulti…
Zero-Shot Generalization during Instruction Tuning: Insights from Similarity and Granularity
Understanding alignment techniques begins with comprehending zero-shot generalization brought by instruction tuning, but little of the mechanism has been understood. Existing work has largely been confined to the task le…
Continual LearningZero-shot GeneralizationInstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning
Instruction tuning is an emergent paradigm in NLP wherein natural language instructions are leveraged with language models to induce zero-shot performance on unseen tasks. Instructions have been shown to enable good perf…
Dialogue EvaluationDialogue GenerationIntent DetectionNatural Language Understanding+2MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning
Instruction tuning, a new learning paradigm that fine-tunes pre-trained language models on tasks specified through instructions, has shown promising zero-shot performance on various natural language processing tasks. How…
SensitivityTransfer LearningZero-Shot Learning