| Challenge: | Effective information retrieval (IR) in settings with limited training data remains a challenging task. |
| Approach: | They propose a technique for reducing overfitting during synthetic data generation . they use DORIS-MAE, ArguAna, and WhatsThatBook as examples . |
| Outcome: | The proposed technique outperforms previous methods and reduces cost by 50% on three recent IR tasks characterized by complex queries. |
Similar Papers
Negative Sampling Techniques in Dense Retrieval: A Survey (2026.findings-eacl)
Copied to clipboard
| Challenge: | Information Retrieval (IR) is fundamental to many modern NLP applications. |
| Approach: | They propose a taxonomy that categorizes negative sampling techniques in dense IR . they analyze them with respect to trade-offs between effectiveness, computational cost, implementation difficulty . |
| Outcome: | The proposed taxonomy categorizes techniques using random, static/dynamically mined, and synthetic datasets. |
Exploring efficient zero-shot synthetic dataset generation for Information Retrieval (2024.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in large language models offer a new avenue of generating synthetic training data to train neural retrieval models for unlabelled data collections. |
| Approach: | They propose a method to generate high-quality synthetic datasets using a small language model and a filtering mechanism to ensure the quality of generated questions. |
| Outcome: | The proposed method outperforms unsupervised retrieval methods such as BM25 and pretrained monoT5. |
Towards Robust Neural Retrieval with Source Domain Synthetic Pre-Finetuning (2022.coling-1)
Copied to clipboard
Revanth Gangi Reddy, Vikas Yadav, Md Arafat Sultan, Martin Franz, Vittorio Castelli, Heng Ji, Avirup Sil
| Challenge: | Existing neural IR systems rely on lexical matching for query-passage alignment, while masked language models use a dual encoder architecture to encode passages and questions into continuous vector representations. |
| Approach: | They propose to enhance the out-of-domain generalization of Dense Passage Retrieval (DPR) through synthetic data augmentation only in the source domain. |
| Outcome: | The proposed model outperforms existing models in in-domain and zero-shot evaluations on Wikipedia-based datasets. |
DiffusionRet: Diffusion-Enhanced Generative Retriever using Constrained Decoding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Generative retrieval methods have suffered from the lack of the intermediate reasoning step . generative retrieval uses sequence-to-sequence diffusion models to map a query to relevant docids . |
| Approach: | They propose a novel method that uses query as an intermediate step before retrieval . they propose to use sequence-to-sequence diffusion models to map a query to relevant docids . |
| Outcome: | Experiments show that proposed method outperforms existing methods on MARCO and Natural Questions datasets. |
It’s All Relative! – A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large language models generate synthetic query-document pairs by prompting with as few as 8 demonstrations. |
| Approach: | They propose to generate queries simultaneously for different labels by prompting with 8 demonstrations. |
| Outcome: | Extensive experimentation shows that synthetic queries generated in such a fashion improve performance. |
Query2doc: Query Expansion with Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for sparse and dense retrieval have limited success on popular datasets. |
| Approach: | They propose a query expansion approach that generates pseudo-documents by few-shot prompting large language models and then expands the query with generated pseudo-docs. |
| Outcome: | The proposed method boosts the performance of BM25 on ad-hoc IR datasets by 3% to 15% without any model fine-tuning. |
On Synthetic Data Strategies for Domain-Specific Generative Retrieval (2025.acl-long)
Copied to clipboard
| Challenge: | Generative retrieval models can be used to generate ranked lists of potentially relevant document identifiers for a user query. |
| Approach: | They propose a synthetic data generation strategy for a two-stage training framework that focuses on learning to decode document identifiers from queries and a strategy for mining hard negatives based on initial model's predictions. |
| Outcome: | The proposed model can generate ranked lists of potentially relevant document identifiers for a user query and then refine ranking through preference learning. |
Beyond [CLS] through Ranking by Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent work on generative ranking models for Information Retrieval has focused on discriminative methods that learn a similarity function to compare questions and candidates answers. |
| Approach: | They propose to use a language model to train a ranking function that model the semantic similarity of documents and queries instead of discriminative ranking functions. |
| Outcome: | The proposed approaches are as effective as state-of-the-art discriminative models for the answer selection task and show unlikelihood losses are reduced for IR. |
Reinforced IR: A Self-Boosting Framework For Domain-Adapted Information Retrieval (2025.acl-long)
Copied to clipboard
| Challenge: | Existing retrieval methods struggle with highly specialized situations that require extensive domain expertise. |
| Approach: | They propose a method that integrates additional information from an LLM-based generator to enhance query performance and train the retriever to better discriminate the relevant documents identified by the generator. |
| Outcome: | The proposed method outperforms existing domain adaptation methods by a large margin and leads to substantial improvements in retrieval quality across a wide range of application scenarios. |
LimRank: Less is More for Reasoning-Intensive Information Reranking (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to rerank information require large-scale fine-tuning, which is computationally expensive. |
| Approach: | They propose an open-source pipeline for generating diverse, challenging, and realistic reranking examples. |
| Outcome: | The proposed model performs competitively on two benchmarks, while being trained on less than 5% of the data typically used in prior work. |