Related papers: ImpliRet: Benchmarking the Implicit Fact Retrieval…

Natural language processing (NLP) techniques have been widely applied in the requirements engineering (RE) field to support tasks such as classification and ambiguity detection. Although RE research is rooted in empirical investigation, it…

Reasoning-intensive retrieval aims to surface evidence that supports downstream reasoning rather than merely matching topical similarity. This capability is increasingly important for agentic search systems, where retrievers must provide…

Natural Language Inference (NLI) is a central task in natural language understanding with applications in fact-checking, question answering, and information retrieval. Despite its importance, current NLI systems heavily rely on supervised…

Modern information retrieval is transitioning from simple document filtering to complex, neuro-symbolic reasoning workflows. However, current retrieval architectures face a fundamental efficiency dilemma when handling the rigorous logical…

With over 200 million published academic documents and millions of new documents being written each year, academic researchers face the challenge of searching for information within this vast corpus. However, existing retrieval systems…

Retrieval-augmented Generation (RAG) has primarily been studied in limited settings, such as factoid question answering; more challenging, reasoning-intensive benchmarks have seen limited success from minimal RAG. In this work, we challenge…

Large language models (LLMs) are widely used, but they often generate subtle factual errors, especially in long-form text. These errors are fatal in some specialized domains such as medicine. Existing fact-checking with grounding documents…

Pseudo-relevance feedback mechanisms, from Rocchio to the relevance models, have shown the usefulness of expanding and reweighting the users' initial queries using information occurring in an initial set of retrieved documents, known as the…

Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically…

Retrieving user-specified objects from complex scenes remains a challenging task, especially when queries are ambiguous or involve multiple similar objects. Existing open-vocabulary detectors operate in a one-shot manner, lacking the…

Argument retrieval is the task of finding relevant arguments for a given query. While existing approaches rely solely on the semantic alignment of queries and arguments, this first shared task on perspective argument retrieval incorporates…

Multiple neural language models have been developed recently, e.g., BERT and XLNet, and achieved impressive results in various NLP tasks including sentence classification, question answering and document ranking. In this paper, we explore…

The central challenge of reasoning-intensive retrieval lies in identifying implicitreasoning relationships between queries and documents, rather than superficial se-mantic or lexical similarity. The contrastive learning paradigm is…

We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization. Finding an optimal portfolio of retrieved items is a combinatorial optimization problem, generally…

The crucial role of the evaluation in the development of the information retrieval tools is useful evidence to improve the performance of these tools and the quality of results that they return. However, the classic evaluation approaches…

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…

AI researchers and practitioners increasingly apply large language models (LLMs) to what we call reasoning-intensive regression (RiR), i.e., deducing subtle numerical scores from text. Unlike standard language regression tasks such as…

While advancements in NLP have significantly improved the performance of Large Language Models (LLMs) on tasks requiring vertical thinking, their lateral thinking capabilities remain under-explored and challenging to measure due to the…

Fully comprehending scientific papers by machines reflects a high level of Artificial General Intelligence, requiring the ability to reason across fragmented and heterogeneous sources of information, presenting a complex and practically…

Despite strong performance on existing benchmarks, it remains unclear whether large language models can reason over genuinely novel scientific information. Most evaluations score end-to-end RAG pipelines, where reasoning is confounded with…