相关论文: Enhancing Factuality through Consensus and Consist…

Existing approaches to automatic summarization assume that a length limit for the summary is given, and view content selection as an optimization problem to maximize informativeness and minimize redundancy within this budget. This framework…

Reranking algorithms have made progress in improving document retrieval quality by efficiently aggregating relevance judgments generated by large language models (LLMs). However, identifying relevant documents for queries that require…

As the amount of user-generated textual content grows rapidly, text summarization algorithms are increasingly being used to provide users a quick overview of the information content. Traditionally, summarization algorithms have been…

When applied to question answering and other text generation tasks, language models (LMs) may be queried generatively (by sampling answers from their output distribution) or discriminatively (by using them to score or rank a set of…

Despite their outstanding performance in the majority of scenarios, contemporary language models still occasionally generate undesirable outputs, for example, hallucinated text. While such behaviors have previously been linked to…

Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Recent work has tied…

Text summarization models are often trained to produce summaries that meet human quality requirements. However, the existing evaluation metrics for summary text are only rough proxies for summary quality, suffering from low correlation with…

Language models can be sampled multiple times to access the distribution underlying their responses, but existing methods cannot efficiently synthesize rich epistemic signals across different long-form responses. We introduce Consensus…

Information retrieval (IR) for precision medicine (PM) often involves looking for multiple pieces of evidence that characterize a patient case. This typically includes at least the name of a condition and a genetic variation that applies to…

Factual consistency is an essential quality of text summarization models in practical settings. Existing work in evaluating this dimension can be broadly categorized into two lines of research, entailment-based and question answering…

Practical applications of abstractive summarization models are limited by frequent factual inconsistencies with respect to their input. Existing automatic evaluation metrics for summarization are largely insensitive to such errors. We…

Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for…

Text summarization is a user-preference based task, i.e., for one document, users often have different priorities for summary. As a key aspect of customization in summarization, granularity is used to measure the semantic coverage between…

While document summarization with LLMs has enhanced access to textual information, concerns about the factual accuracy of these summaries persist, especially in the medical domain. Tracing evidence from which summaries are derived enables…

Automatically condensing multiple topic-related scientific papers into a succinct and concise summary is referred to as Multi-Document Scientific Summarization (MDSS). Currently, while commonly used abstractive MDSS methods can generate…

This work addresses the challenge of factual consistency in text generation systems. We unify the tasks of Natural Language Inference, Summarization Evaluation, Factuality Verification and Factual Consistency Evaluation to train models…

Multi-document summarization is the process of automatically generating a concise summary of multiple documents related to the same topic. This summary can help users quickly understand the key information from a large collection of…

Minimum Bayes Risk (MBR) decoding has seen renewed interest as an alternative to traditional generation strategies. While MBR has proven effective in machine translation, where the variability of a language model's outcome space is…

Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…

Retrieval-augmented generation (RAG) systems trained using reinforcement learning (RL) with reasoning are hampered by inefficient context management, where long, noisy retrieved documents increase costs and degrade performance. We introduce…