Related papers: DataDignity: Training Data Attribution for Large L…

Trustworthy language models should provide both correct and verifiable answers. However, citations generated directly by standalone LLMs are often unreliable. As a result, current systems insert citations by querying an external retriever…

Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting evidence unchecked. This answer-only approach masks a critical…

Question Answering (QA) tasks requiring information from multiple documents often rely on a retrieval model to identify relevant information for reasoning. The retrieval model is typically trained to maximize the likelihood of the labeled…

Document retrieval is a core component of many knowledge-intensive natural language processing task formulations such as fact verification and question answering. Sources of textual knowledge, such as Wikipedia articles, condition the…

While increasingly complex approaches to question answering (QA) have been proposed, the true gain of these systems, particularly with respect to their expensive training requirements, can be inflated when they are not compared to adequate…

Knowledge-Based Visual Question Answering (KB-VQA) requires models to answer questions about an image by integrating external knowledge, posing significant challenges due to noisy retrieval and the structured, encyclopedic nature of the…

Large Language Models (LLMs) are trained on vast amounts of data, most of which is automatically scraped from the internet. This data includes encyclopedic documents that harbor a vast amount of general knowledge (e.g., Wikipedia) but also…

Classifier-based Quality Filtering has recently emerged as a fundamental technique in constructing pre-training corpora. The ability to deploy a single model that can replace or supplement a set of heuristics has proven effective across…

Scaling laws predict that the performance of large language models improves with increasing model size and data size. In practice, pre-training has been relying on massive web crawls, using almost all data sources publicly available on the…

This paper explores new methods for locating the sources used to write a text, by fine-tuning a variety of language models to rerank candidate sources. After retrieving candidates sources using a baseline BM25 retrieval model, a variety of…

Online encyclopediae like Wikipedia contain large amounts of text that need frequent corrections and updates. The new information may contradict existing content in encyclopediae. In this paper, we focus on rewriting such dynamically…

Retrieval Augmented Generation (RAG) works as a backbone for interacting with an enterprise's own data via Conversational Question Answering (ConvQA). In a RAG system, a retriever fetches passages from a collection in response to a…

LLMs are known to store vast amounts of knowledge in their parametric memory. However, learning and recalling facts from this memory is known to be unreliable, depending largely on the prevalence of particular facts in the training data and…

Retrieval systems often fail when user queries differ stylistically or semantically from the language used in domain documents. Query rewriting has been proposed to bridge this gap, improving retrieval by reformulating user queries into…

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…

Fake information poses one of the major threats for society in the 21st century. Identifying misinformation has become a key challenge due to the amount of fake news that is published daily. Yet, no approach is established that addresses…

In this paper we introduce a new publicly available dataset for verification against textual sources, FEVER: Fact Extraction and VERification. It consists of 185,445 claims generated by altering sentences extracted from Wikipedia and…

Over the last few years, verifying the credibility of information sources has become a fundamental need to combat disinformation. Here, we present a language-agnostic model designed to assess the reliability of web domains as sources in…

Autoregressive language models are widely used for text evaluation, however, their left-to-right factorization introduces positional bias, i.e., early tokens are scored with only leftward context, conflating architectural asymmetry with…

There is growing evidence that pretraining on high quality, carefully thought-out tokens such as code or mathematics plays an important role in improving the reasoning abilities of large language models. For example, Minerva, a PaLM model…