Related papers: Improving Factual Consistency Between a Response a…
The rapid dissemination of misinformation through social media increased the importance of automated fact-checking. Furthermore, studies on what deep neural models pay attention to when making predictions have increased in recent years.…
Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log-likelihood of ground-truth questions using teacher forcing. However, this training objective is inconsistent with…
While improving neural dialogue agents' factual accuracy is the object of much research, another important aspect of communication, less studied in the setting of neural dialogue, is transparency about ignorance. In this work, we analyze to…
Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewards provide only coarse supervision and cannot distinguish correct from incorrect…
Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…
Video captioning aims to describe events in a video with natural language. In recent years, many works have focused on improving captioning models' performance. However, like other text generation tasks, it risks introducing factual errors…
Improving factual consistency of abstractive summarization has been a widely studied topic. However, most of the prior works on training factuality-aware models have ignored the negative effect it has on summary quality. We propose EFACTSUM…
Statistical spoken dialogue systems have the attractive property of being able to be optimised from data via interactions with real users. However in the reinforcement learning paradigm the dialogue manager (agent) often requires…
Large Language Models (LLMs) can produce verbalized self-explanations, yet prior studies suggest that such rationales may not reliably reflect the model's true decision process. We ask whether these explanations nevertheless help users…
Neural abstractive summarization models are able to generate summaries which have high overlap with human references. However, existing models are not optimized for factual correctness, a critical metric in real-world applications. In this…
Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled…
Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leveraging reward models. In practice, these models often…
Improvements in large language models have led to increasing optimism that they can serve as reliable evaluators of natural language generation outputs. In this paper, we challenge this optimism by thoroughly re-evaluating five…
The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually…
Quotations are crucial for successful explanations and persuasions in interpersonal communications. However, finding what to quote in a conversation is challenging for both humans and machines. This work studies automatic quotation…
Fact-based dialogue generation is a task of generating a human-like response based on both dialogue context and factual texts. Various methods were proposed to focus on generating informative words that contain facts effectively. However,…
In this paper, we show that counterfactual explanations of confidence scores help users better understand and better trust an AI model's prediction in human-subject studies. Showing confidence scores in human-agent interaction systems can…
Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. Such biases can produce suboptimal samples, skewed outcomes, and unfairness, with potentially serious consequences.…
We propose a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including health, law, finance and politics. We crafted questions that…
Recent approaches to question generation have used modifications to a Seq2Seq architecture inspired by advances in machine translation. Models are trained using teacher forcing to optimise only the one-step-ahead prediction. However, at…