Related papers: SEEK: Semantic Evidence Extraction via Adaptive Ch…

Chunking is a crucial preprocessing step in retrieval-augmented generation (RAG) systems, significantly impacting retrieval effectiveness across diverse datasets. In this study, we systematically evaluate fixed-size chunking strategies and…

Retrieving external knowledge and prompting large language models with relevant information is an effective paradigm to enhance the performance of question-answering tasks. Previous research typically handles paragraphs from external…

Visual Entailment with natural language explanations aims to infer the relationship between a text-image pair and generate a sentence to explain the decision-making process. Previous methods rely mainly on a pre-trained vision-language…

Event Argument extraction refers to the task of extracting structured information from unstructured text for a particular event of interest. The existing works exhibit poor capabilities to extract causal event arguments like Reason and…

Fact verification plays a vital role in combating misinformation by assessing the veracity of claims through evidence retrieval and reasoning. However, traditional methods struggle with complex claims requiring multi-hop reasoning over…

Lexical and semantic matches are commonly used as relevance measurements for information retrieval. Together they estimate the semantic equivalence between the query and the candidates. However, semantic equivalence is not the only…

Many use cases require retrieving smaller portions of text, and dense vector-based retrieval systems often perform better with shorter text segments, as the semantics are less likely to be over-compressed in the embeddings. Consequently,…

Query expansion is an effective approach for mitigating vocabulary mismatch between queries and documents in information retrieval. One recent line of research uses language models to generate query-related contexts for expansion. Along…

We present the first large-scale, cross-domain evaluation of document chunking strategies for dense retrieval, addressing a critical but underexplored aspect of retrieval-augmented systems. In our study, 36 segmentation methods spanning…

Retrieval-Augmented Generation (RAG) systems lose retrieval accuracy when similar documents coexist in the vector database, causing unnecessary information, hallucinations, and factual errors. To alleviate this issue, we propose CHOP, a…

Compounding is a highly productive word-formation process in some languages that is often problematic for natural language processing applications. In this paper, we investigate whether distributional semantics in the form of word…

The increasing concern with misinformation has stimulated research efforts on automatic fact checking. The recently-released FEVER dataset introduced a benchmark fact-verification task in which a system is asked to verify a claim using…

Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline. This paper initially introduces a dual-metric evaluation…

This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain. In doing so, we make two contributions: first, we provide datasets for multilingual probing, derived from Wikipedia, in five…

The rapid proliferation of misinformation across online platforms underscores the urgent need for robust, up-to-date, explainable, and multilingual fact-checking resources. However, existing datasets are limited in scope, often lacking…

Generative AI models exhibit remarkable potential; however, hallucinations across various tasks present a significant challenge, particularly for longer inputs that current approaches struggle to address effectively. We introduce SCALE…

Selecting which claims to check is a time-consuming task for human fact-checkers, especially from documents consisting of multiple sentences and containing multiple claims. However, existing claim extraction approaches focus more on…

Document chunking is a critical preprocessing step in dense retrieval systems, yet the design space of chunking strategies remains poorly understood. Recent research has proposed several concurrent approaches, including LLM-guided methods…

Information verification is quite a challenging task, this is because many times verifying a claim can require picking pieces of information from multiple pieces of evidence which can have a hierarchy of complex semantic relations.…

Pretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model distillation with parallel data. However, it remains unclear…