Related papers: Enhancing Retrieval Systems with Inference-Time Lo…
Conversational search seeks to retrieve relevant passages for the given questions in conversational question answering. Conversational Query Reformulation (CQR) improves conversational search by refining the original queries into…
One of the challenges in information retrieval is providing accurate answers to a user's question often expressed as uncertainty words. Most answers are based on a Syntactic approach rather than a Semantic analysis of the query. In this…
Datalog reasoning based on the semina\"ive evaluation strategy evaluates rules using traditional join plans, which often leads to redundancy and inefficiency in practice, especially when the rules are complex. Hypertree decompositions help…
Advancements in Large Language Models (LLMs) have extended their input context length, yet they still struggle with retrieval and reasoning in long-context inputs. Existing methods propose to utilize the prompt strategy and retrieval head…
Generating logical form equivalents of human language is a fresh way to employ neural architectures where long short-term memory effectively captures dependencies in both encoder and decoder units. The logical form of the sequence usually…
Legal case retrieval, which aims to retrieve relevant cases to a given query case, benefits judgment justice and attracts increasing attention. Unlike generic retrieval queries, legal case queries are typically long and the definition of…
Classification is a common AI problem, and vector search is a typical solution. This transforms a given body of text into a numerical representation, known as an embedding, and modern improvements to vector search focus on optimising speed…
Retrieval Augmented Generation (RAG) is a promising technique for mitigating two key limitations of large language models (LLMs): outdated information and hallucinations. RAG system stores documents as embedding vectors in a database. Given…
Recent language models enable new opportunities for structured reasoning with text, such as the construction of intuitive, proof-like textual entailment trees without relying on brittle formal logic. However, progress in this direction has…
Analytical information needs, such as trend analysis and causal impact assessment, are prevalent across various domains including law, finance, science, and much more. However, existing information retrieval paradigms, whether based on…
Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these procedures are often misaligned in that training objectives do not…
Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document. Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the…
LLMs have fundamentally transformed dense retrieval, upgrading backbones from discriminative encoders to generative architectures. However, a critical disconnect remains: while LLMs possess strong reasoning capabilities, current retrievers…
In this position paper, we propose a reasoning framework that can model the reasoning process underlying natural language inferences. The framework is based on the semantic tableau method, a well-studied proof system in formal logic. Like…
Time is an important relevance signal when searching streams of social media posts. The distribution of document timestamps from the results of an initial query can be leveraged to infer the distribution of relevant documents, which can…
Inference-time scaling has emerged as a powerful alternative to parameter scaling for improving language model performance on complex reasoning tasks. While existing methods have shown strong performance gains under fixed compute budgets,…
Document retrieval has been an important research problem over many years in the information retrieval community. State-of-the-art techniques utilize various methods in matching documents to a given document including keywords, phrases, and…
In real practice, questions are typically complex and knowledge-intensive, requiring Large Language Models (LLMs) to recognize the multifaceted nature of the question and reason across multiple information sources. Iterative and adaptive…
Recent advances in large language models have enabled the development of viable generative retrieval systems. Instead of a traditional document ranking, generative retrieval systems often directly return a grounded generated text as a…
Reading comprehension models are based on recurrent neural networks that sequentially process the document tokens. As interest turns to answering more complex questions over longer documents, sequential reading of large portions of text…