Related papers: Optimising Factual Consistency in Summarisation vi…

Foundation models encompass an extensive knowledge base and offer remarkable transferability. However, this knowledge becomes outdated or insufficient over time. The challenge lies in continuously updating foundation models to accommodate…

Learning from human preferences is important for language models to match human needs and to align with human and social values. Prior works have achieved remarkable successes by learning from human feedback to understand and follow…

We focus on learning the desired objective function for a robot. Although trajectory demonstrations can be very informative of the desired objective, they can also be difficult for users to provide. Answers to comparison queries, asking…

Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is…

LLM-based explainable recommenders can produce fluent explanations that are factually correct, yet still justify items using attributes that conflict with a user's historical preferences. Such preference-inconsistent explanations yield…

The growth of online consumer health questions has led to the necessity for reliable and accurate question answering systems. A recent study showed that manual summarization of consumer health questions brings significant improvement in…

A key challenge for abstractive summarization is ensuring factual consistency of the generated summary with respect to the original document. For example, state-of-the-art models trained on existing datasets exhibit entity hallucination,…

Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize toward a reference policy. Despite their effectiveness, the effects of sampling and…

A prominent weakness of modern language models (LMs) is their tendency to generate factually incorrect text, which hinders their usability. A natural question is whether such factual errors can be detected automatically. Inspired by…

Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "helpfulness" and "harmfulness". In our work, we instead propose…

We study unsupervised multi-document summarization evaluation metrics, which require neither human-written reference summaries nor human annotations (e.g. preferences, ratings, etc.). We propose SUPERT, which rates the quality of a summary…

As counterfactual examples become increasingly popular for explaining decisions of deep learning models, it is essential to understand what properties quantitative evaluation metrics do capture and equally important what they do not…

E-commerce stores collect customer feedback to let sellers learn about customer concerns and enhance customer order experience. Because customer feedback often contains redundant information, a concise summary of the feedback can be…

While fine-tuning is the standard for injecting factual knowledge into large language models (LLMs), the mechanisms enabling reliable fact recall via unseen queries remain poorly understood. Common two-stage training strategies, which…

A crucial issue of current text generation models is that they often uncontrollably generate factually inconsistent text with respective of their inputs. Limited by the lack of annotated data, existing works in evaluating factual…

A key challenge in Multi-Document Summarization (MDS) is effectively integrating information from multiple sources while maintaining coherence and topical relevance. While Large Language Models have shown impressive results in…

Pretrained language models can encode a large amount of knowledge and utilize it for various reasoning tasks, yet they can still struggle to learn novel factual knowledge effectively from finetuning on limited textual demonstrations. In…

We introduce The FACTS Leaderboard, an online leaderboard suite and associated set of benchmarks that comprehensively evaluates the ability of language models to generate factually accurate text across diverse scenarios. The suite provides…

Product reviews significantly influence purchasing decisions on e-commerce platforms. However, the sheer volume of reviews can overwhelm users, obscuring the information most relevant to their specific needs. Current e-commerce…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…