Related papers: Empowering Dual-Encoder with Query Generator for C…

Entity Linking has two main open areas of research: 1) generate candidate entities without using alias tables and 2) generate more contextual representations for both mentions and entities. Recently, a solution has been proposed for the…

In the recent years, the dual-encoder vision-language models (\eg CLIP) have achieved remarkable text-to-image retrieval performance. However, we discover that these models usually results in very different retrievals for a pair of…

This paper presents our system for SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval. In an era where misinformation spreads rapidly, effective fact-checking is increasingly critical. We introduce TriAligner, a…

In this paper, we propose a new dense retrieval model which learns diverse document representations with deep query interactions. Our model encodes each document with a set of generated pseudo-queries to get query-informed, multi-view…

Recent work has shown that more effective dense retrieval models can be obtained by distilling ranking knowledge from an existing base re-ranking model. In this paper, we propose a generic curriculum learning based optimization framework…

We present an approach to ranking with dense representations that applies knowledge distillation to improve the recently proposed late-interaction ColBERT model. Specifically, we distill the knowledge from ColBERT's expressive MaxSim…

Dense retrieval models use bi-encoder network architectures for learning query and document representations. These representations are often in the form of a vector representation and their similarities are often computed using the dot…

Rerankers play a critical role in multimodal Retrieval-Augmented Generation (RAG) by refining ranking of an initial set of retrieved documents. Rerankers are typically trained using hard negative mining, whose goal is to select pages for…

Dense retrievers in retrieval-augmented generation (RAG) systems exhibit systematic biases -- including brevity, position, literal matching, and repetition biases -- that can compromise retrieval quality. Query rewriting techniques are now…

Multilingual text-video retrieval methods have improved significantly in recent years, but the performance for other languages lags behind English. We propose a Cross-Lingual Cross-Modal Knowledge Distillation method to improve multilingual…

This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…

Retrieval of previously fact-checked claims is a well-established task, whose automation can assist professional fact-checkers in the initial steps of information verification. Previous works have mostly tackled the task monolingually,…

Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous…

In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final performance, it is important to…

Pre-trained code models have emerged as the state-of-the-art paradigm for code search tasks. The paradigm involves pre-training the model on search-irrelevant tasks such as masked language modeling, followed by the fine-tuning stage, which…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

To ensure large language models (LLMs) are used safely, one must reduce their propensity to hallucinate or to generate unacceptable answers. A simple and often used strategy is to first let the LLM generate multiple hypotheses and then…

Modern search systems use several large ranker models with transformer architectures. These models require large computational resources and are not suitable for usage on devices with limited computational resources. Knowledge distillation…

Tool retrieval over large API catalogs is a core bottleneck for LLM agents: user queries arrive in colloquial, often underspecified language, while the catalog uses technical API vocabulary that no fixed encoder can bridge on its own. The…

Multiple-choice questions (MCQs) are commonly used across all levels of math education since they can be deployed and graded at a large scale. A critical component of MCQs is the distractors, i.e., incorrect answers crafted to reflect…