Related papers: Unified Generative & Dense Retrieval for Query Rew…

Reinforcement learning (RL) has emerged as a critical technique for enhancing LLM-based deep search agents. However, existing approaches primarily rely on binary outcome rewards, which fail to capture the comprehensiveness and factuality of…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but still suffers from long contexts and disjoint retrieval-generation optimization. In this work, we propose CLaRa (Continuous Latent…

Information retrieval plays a crucial role in resource localization. Current dense retrievers retrieve the relevant documents within a corpus via embedding similarities, which compute similarities between dense vectors mainly depending on…

This contribution summarizes the participation of the UNIMIB team to the TREC 2021 Clinical Trials Track. We have investigated the effect of different query representations combined with several retrieval models on the retrieval…

Realistic text-to-SQL workflows often require joining multiple tables. As a result, accurately retrieving the relevant set of tables becomes a key bottleneck for end-to-end performance. We study an open-book setting where queries must be…

Cross-lingual sponsored search is crucial for global advertising platforms, where users from different language backgrounds interact with multilingual ads. Traditional machine translation methods often fail to capture query-specific…

In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review…

Retrieval augmented generation has revolutionized large language model (LLM) outputs by providing factual supports. Nevertheless, it struggles to capture all the necessary knowledge for complex reasoning questions. Existing retrieval…

BERT-based re-ranking and dense retrieval (DR) systems have been shown to improve search effectiveness for spoken content retrieval (SCR). However, both methods can still show a reduction in effectiveness when using ASR transcripts in…

Retrieval Augmented Generation (RAG) is a technique used to augment Large Language Models (LLMs) with contextually relevant, time-critical, or domain-specific information without altering the underlying model parameters. However,…

We investigate the exploitation of both lexical and neural relevance signals for ad-hoc passage retrieval. Our exploration involves a large-scale training dataset in which dense neural representations of MS-MARCO queries and passages are…

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access broader knowledge sources, yet factual inconsistencies persist due to noise in retrieved documents-even with advanced retrieval methods. We demonstrate that…

Large language models (LLMs) under-perform on low-resource languages due to limited training data. We present a method to efficiently collect text data for low-resource languages from the entire Common Crawl corpus. Our approach,…

Conversational search aims to satisfy users' complex information needs via multiple-turn interactions. The key challenge lies in revealing real users' search intent from the context-dependent queries. Previous studies achieve conversational…

Unit testing validates the correctness of the units of the software system under test and serves as the cornerstone in improving software quality and reliability. To reduce manual efforts in writing unit tests, some techniques have been…

Recently, information retrieval has seen the emergence of dense retrievers, using neural networks, as an alternative to classical sparse methods based on term-frequency. These models have obtained state-of-the-art results on datasets and…

Dense retrieval (DR) has the potential to resolve the query understanding challenge in conversational search by matching in the learned embedding space. However, this adaptation is challenging due to DR models' extra needs for supervision…

Retrieval-Augmented Generation (RAG) merges retrieval methods with deep learning advancements to address the static limitations of large language models (LLMs) by enabling the dynamic integration of up-to-date external information. This…

Reasoning-augmented search agents such as Search-R1, trained via reinforcement learning with verifiable rewards (RLVR), demonstrate remarkable capabilities in multi-step information retrieval from external knowledge sources. These agents…

A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows. The neural IR community made great advancements in training effective dual-encoder…