Related papers: CoP: Factual Inconsistency Detection by Controllin…
Automated fact checking systems have been proposed that quickly provide veracity prediction at scale to mitigate the negative influence of fake news on people and on public opinion. However, most studies focus on veracity classifiers of…
Large Language Models have significantly advanced natural language processing tasks, but remain prone to generating incorrect or misleading but plausible arguments. This issue, known as hallucination, is particularly concerning in…
We analyze the structure of the disagreement among a population of voters over a set of alternatives. Surveys typically ask either for pairwise comparisons, simple and intuitive for participants, or full rankings over alternatives,…
Conformal methods provide prediction sets for outcomes with confidence guarantees. We study their use in a selective inference setting, where inference is performed only when the prediction set is informative. The analyst may consider as…
Prompt learning is an effective paradigm that bridges gaps between the pre-training tasks and the corresponding downstream applications. Approaches based on this paradigm have achieved great transcendent results in various applications.…
Predictive inference is a fundamental task in statistics, traditionally addressed using parametric assumptions about the data distribution and detailed analyses of how models learn from data. In recent years, conformal prediction has…
Recent studies have demonstrated the potential to control paraphrase generation, such as through syntax, which has broad applications in various downstream tasks. However, these methods often require detailed parse trees or syntactic…
Abstractive summarization aims at generating natural language summaries of a source document that are succinct while preserving the important elements. Despite recent advances, neural text summarization models are known to be susceptible to…
For summarization, human preference is critical to tame outputs of the summarizer in favor of human interests, as ground-truth summaries are scarce and ambiguous. Practical settings require dynamic exchanges between human and AI agent…
Implicit feedback is the simplest form of user feedback that can be used for item recommendation. It is easy to collect and is domain independent. However, there is a lack of negative examples. Previous work tackles this problem by assuming…
This paper clarifies a fundamental difference between causal inference and traditional statistical inference by formalizing a mathematical distinction between their respective parameters. We connect two major approaches to causal inference,…
Despite recent success, large neural models often generate factually incorrect text. Compounding this is the lack of a standard automatic evaluation for factuality--it cannot be meaningfully improved if it cannot be measured. Grounded…
The topic of summarization evaluation has recently attracted a surge of attention due to the rapid development of abstractive summarization systems. However, the formulation of the task is rather ambiguous, neither the linguistic nor the…
Extractive summaries are usually presented as lists of sentences with no expected cohesion between them and with plenty of redundant information if not accounted for. In this paper, we investigate the trade-offs incurred when aiming to…
Extractive summaries are usually presented as lists of sentences with no expected cohesion between them. In this paper, we aim to enforce cohesion whilst controlling for informativeness and redundancy in summaries, in cases where the input…
Why do language models trained on contradictory data prefer correct answers? In controlled experiments with small transformers (3.5M--86M parameters), we show that this preference tracks the compressibility structure of errors rather than…
We address the problem of unsupervised abstractive summarization of collections of user generated reviews with self-supervision and control. We propose a self-supervised setup that considers an individual document as a target summary for a…
Explainable recommendation through counterfactual reasoning seeks to identify the influential aspects of items in recommendations, which can then be used as explanations. However, state-of-the-art approaches, which aim to minimize changes…
In abstractive summarization, the challenge of producing concise and accurate summaries arises from the vast amount of information contained in the source document. Consequently, although Large Language Models (LLMs) can generate fluent…
Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers. This problem has been extensively studied under the supervised setting,…