Related papers: Extractive Fact Decomposition for Interpretable Na…

An important challenge in statistical analysis lies in controlling the estimation bias when handling the ever-increasing data size and model complexity of modern data settings. In this paper, we propose a reliable estimation and inference…

Table-based reasoning has shown remarkable progress in combining deep models with discrete reasoning, which requires reasoning over both free-form natural language (NL) questions and structured tabular data. However, previous table-based…

Query understanding (QU) aims to accurately infer user intent to improve document retrieval. It plays a vital role in modern search engines. While large language models (LLMs) have made notable progress in this area, their effectiveness has…

Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination -- generating content ungrounded in the realities of training data. Recent work has focused on decoding techniques to improve…

Current Natural Language Inference (NLI) models achieve impressive results, sometimes outperforming humans when evaluating on in-distribution test sets. However, as these models are known to learn from annotation artefacts and dataset…

Attribution is crucial in question answering (QA) with Large Language Models (LLMs).SOTA question decomposition-based approaches use long form answers to generate questions for retrieving related documents. However, the generated questions…

Large Language Models (LLMs) are being increasingly used within data systems to process large datasets with text fields. A broad class of such tasks involves a semantic join-joining two tables based on a natural language predicate per pair…

Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models.…

Large language models (LLMs) have demonstrated remarkable capabilities, but their outputs can sometimes be unreliable or factually incorrect. To address this, we introduce Self Logits Evolution Decoding (SLED), a novel decoding framework…

Natural language explanations play a fundamental role in Natural Language Inference (NLI) by revealing how premises logically entail hypotheses. Recent work has shown that the interaction of large language models (LLMs) with theorem provers…

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

Retrieval-augmented generation (RAG) incorporates external knowledge into large language models (LLMs), improving their adaptability to downstream tasks and enabling information updates. Surprisingly, recent empirical evidence demonstrates…

Large Language Models (LLMs) are increasingly being used in real-world applications. However, concerns about the reliability of the content they generate persist, as it frequently deviates from factual correctness or exhibits deficiencies…

Real-world arguments in text and dialogues are normally enthymemes (i.e. some of their premises and/or claims are implicit). Natural language processing (NLP) methods for handling enthymemes can potentially identify enthymemes in text but…

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

Human tackle reading comprehension not only based on the given context itself but often rely on the commonsense beyond. To empower the machine with commonsense reasoning, in this paper, we propose a Commonsense Evidence Generation and…

We propose a simple neural architecture for natural language inference. Our approach uses attention to decompose the problem into subproblems that can be solved separately, thus making it trivially parallelizable. On the Stanford Natural…

We present a large-scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation captures distinct types of reasoning. The collection results from recasting 13…

As large language models become increasingly capable, there is growing concern that they may develop reasoning processes that are encoded or hidden from human oversight. To investigate whether current interpretability techniques can…

Explanation constitutes an archetypal feature of human rationality, underpinning learning and generalisation, and representing one of the media supporting scientific discovery and communication. Due to the importance of explanations in…