Related papers: On Coherence-based Predictors for Dense Query Perf…
Search query classification, as an effective way to understand user intents, is of great importance in real-world online ads systems. To ensure a lower latency, a shallow model (e.g. FastText) is widely used for efficient online inference.…
Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…
Prompt-based learning's efficacy across numerous natural language processing tasks has led to its integration into dense passage retrieval. Prior research has mainly focused on enhancing the semantic understanding of pre-trained language…
The search of information in large text repositories has been plagued by the so-called document-query vocabulary gap, i.e. the semantic discordance between the contents in the stored document entities on the one hand and the human query on…
Knowledge Tracing (KT) models students' knowledge states based on learning interactions to predict performance. While deep learning-based KT models have boosted predictive accuracy, most models rely on deterministic vector embeddings and…
Programming Knowledge Tracing (PKT) has recently advanced through hybrid approaches that integrate attention-based feature modeling for code representation with RNN-based sequential prediction. While these models report strong empirical…
Comprehensively understanding and accurately predicting the performance of large language models across diverse downstream tasks has emerged as a pivotal challenge in NLP research. The pioneering scaling law on downstream works demonstrated…
Dense retrieval is a basic building block of information retrieval applications. One of the main challenges of dense retrieval in real-world settings is the handling of queries containing misspelled words. A popular approach for handling…
Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized…
With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most…
Retrieval and ranking models are the backbone of many applications such as web search, open domain QA, or text-based recommender systems. The latency of neural ranking models at query time is largely dependent on the architecture and…
Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb--a hierarchy-aware framework--to organize sentence…
Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabilities. Evaluating open-source LLMs through leaderboards faces persistent issues like data…
Information retrieval involves selecting artifacts from a corpus that are most relevant to a given search query. The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and…
The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and…
Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be…
Query expansion is a method for alleviating the vocabulary mismatch problem present in information retrieval tasks. Previous works have shown that terms selected for query expansion by traditional methods such as pseudo-relevance feedback…
Parameter Efficient Fine-Tuning (PEFT) methods have been extensively utilized in Large Language Models (LLMs) to improve the down-streaming tasks without the cost of fine-tuing the whole LLMs. Recent studies have shown how to effectively…
Recently, Information Retrieval community has witnessed fast-paced advances in Dense Retrieval (DR), which performs first-stage retrieval with embedding-based search. Despite the impressive ranking performance, previous studies usually…
We investigate improving the retrieval effectiveness of embedding models through the lens of corpus-specific fine-tuning. Prior work has shown that fine-tuning with queries generated using a dataset's retrieval corpus can boost retrieval…