Related papers: NOWJ@COLIEE 2025: A Multi-stage Framework Integrat…
Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with…
Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…
The Knowledge Graph Completion~(KGC) task aims to infer the missing entity from an incomplete triple. Existing embedding-based methods rely solely on triples in the KG, which is vulnerable to specious relation patterns and long-tail…
We demonstrate the efficiencies and explanatory abilities of extensions to the common tools of Autoencoders and LLM interpreters, in the novel context of comparing different cultural approaches to the same international news event. We…
Linking implicit scientific claims made on social media to their original publications is crucial for evidence-based fact-checking and scholarly discourse, yet it is hindered by lexical sparsity, very short queries, and domain-specific…
Large Language Models (LLMs) have shown strong capabilities in document re-ranking, a key component in modern Information Retrieval (IR) systems. However, existing LLM-based approaches face notable limitations, including ranking…
Candidate sourcing for recruiters is best viewed as a two-stage retrieval and reranking pipeline with recall as the primary objective under a limited review budget. An upstream production retriever first returns a candidate shortlist for…
Reasoning-focused large language models (LLMs) are rapidly evolving across various domains, yet their capabilities in handling complex legal problems remains underexplored. In this paper, we introduce Unilaw-R1, a large language model…
Getting an overview over the legal domain has become challenging, especially in a broad, international context. Legal question answering systems have the potential to alleviate this task by automatically retrieving relevant legal texts for…
Traditional multimodal retrieval systems rely primarily on bi-encoder architectures, where performance is closely tied to embedding dimensionality. Recent work, Think-Then-Embed (TTE), shows that incorporating multimodal reasoning to elicit…
LLMs confront inherent limitations in terms of its knowledge, memory, and action. The retrieval augmentation stands as a vital mechanism to address these limitations, which brings in useful information from external sources to augment the…
Recent work has shown that language models scaled to billions of parameters, such as GPT-3, perform remarkably well in zero-shot and few-shot scenarios. In this work, we experiment with zero-shot models in the legal case entailment task of…
We present our submission to the Task 5 of SemEval-2025 that aims to aid librarians in assigning subject tags to the library records by producing a list of likely relevant tags for a given document. We frame the task as an information…
Despite advances in generative large language models (LLMs), practical application of specialized conversational AI agents remains constrained by computation costs, latency requirements, and the need for precise domain-specific relevance…
We propose a two-stage "Mine and Refine" contrastive training framework for semantic text embeddings to enhance multi-category e-commerce search retrieval. Large scale e-commerce search demands embeddings that generalize to long tail, noisy…
Large language models (LLMs) have demonstrated great potential for domain-specific applications, such as the law domain. However, recent disputes over GPT-4's law evaluation raise questions concerning their performance in real-world legal…
This paper presents our submission to the QIAS 2025 shared task on Islamic knowledge understanding and reasoning. We developed a hybrid retrieval-augmented generation (RAG) system that combines sparse and dense retrieval methods with…
This paper describes a hypernym discovery system for our participation in the SemEval-2018 Task 9, which aims to discover the best (set of) candidate hypernyms for input concepts or entities, given the search space of a pre-defined…
Distributed representations of words have shown to be useful to improve the effectiveness of IR systems in many sub-tasks like query expansion, retrieval and ranking. Algorithms like word2vec, GloVe and others are also key factors in many…
Embedding-based code retrieval often suffers when encoders overfit to surface syntax. Prior work mitigates this by using LLMs to rephrase queries and corpora into a normalized style, but leaves two questions open: how much representational…