Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truthfulness and factuality are thus of great interest. To help users make the right decisions about the information they get, LLMs should not only provide information but also help users fact-check it. We conduct human experiments with 80 crowdworkers to compare language models with search engines (information retrieval systems) at facilitating fact-checking. We prompt LLMs to validate a given claim and provide corresponding explanations. Users reading LLM explanations are significantly more efficient than those using search engines while achieving similar accuracy. However, they over-rely on the LLMs when the explanation is wrong. To reduce over-reliance on LLMs, we ask LLMs to provide contrastive information—explain both why the claim is true and false, and then we present both sides of the explanation to users. This contrastive explanation mitigates users’ over-reliance on LLMs, but cannot significantly outperform search engines. Further, showing both search engine results and LLM explanations offers no complementary benefits compared to search engines alone. Taken together, our study highlights that natural language explanations by LLMs may not be a reliable replacement for reading the retrieved passages, especially in high-stakes settings where over-relying on wrong AI explanations could lead to critical consequences.

In the task of entity description generation, given a context and a specified entity, a model must describe that entity correctly and in a contextually-relevant way. In this task, as well as broader language generation tasks, the generation of a nonfactual description (factual error) versus an incongruous description (contextual error) is fundamentally different, yet often conflated. We develop an evaluation paradigm that enables us to disentangle these two types of errors in naturally occurring textual contexts. We find that factuality and congruity are often at odds, and that models specifically struggle with accurate descriptions of entities that are less familiar to people. This shortcoming of language models raises concerns around the trustworthiness of such models, since factual errors on less well-known entities are exactly those that a human reader will not recognize.

NLP systems have shown impressive performance at answering questions by retrieving relevant context. However, with the increasingly large models, it is impossible and often undesirable to constrain models’ knowledge or reasoning to only the retrieved context. This leads to a mismatch between the information that the models access to derive the answer and the information that is available to the user to assess the model predicted answer. In this work, we study how users interact with QA systems in the absence of sufficient information to assess their predictions. Further, we ask whether adding the requisite background helps mitigate users’ over-reliance on predictions. Our study reveals that users rely on model predictions even in the absence of sufficient information needed to assess the model’s correctness. Providing the relevant background, however, helps users better catch model errors, reducing over-reliance on incorrect predictions. On the flip side, background information also increases users’ confidence in their accurate as well as inaccurate judgments. Our work highlights that supporting users’ verification of QA predictions is an important, yet challenging, problem.

Explainable NLP techniques primarily explain by answering “Which tokens in the input are responsible for this prediction?”. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by answering “What differences between the two inputs explain this prediction?”. We introduce a technique to generate contrastive phrasal highlights that explain the predictions of a semantic divergence model via phrase alignment guided erasure. We show that the resulting highlights match human rationales of cross-lingual semantic differences better than popular post-hoc saliency techniques and that they successfully help people detect fine-grained meaning differences in human translations and critical machine translation errors.

Content is created for a well-defined purpose, often described by a metric or signal represented in the form of structured information. The relationship between the goal (metrics) of target content and the content itself is non-trivial. While large-scale language models show promising text generation capabilities, guiding the generated text with external metrics is challenging. These metrics and content tend to have inherent relationships and not all of them may be of consequence. We introduce CaM-Gen: Causally aware Generative Networks guided by user-defined target metrics incorporating the causal relationships between the metric and content features. We leverage causal inference techniques to identify causally significant aspects of a text that lead to the target metric and then explicitly guide generative models towards these by a feedback mechanism. We propose this mechanism for variational autoencoder and Transformer-based generative models. The proposed models beat baselines in terms of the target metric control while maintaining fluency and language quality of the generated text. To the best of our knowledge, this is one of the early attempts at controlled generation incorporating a metric guide using causal inference.

Long documents like contracts, financial documents, etc., are often tedious to read through. Linearly consuming (via scrolling or navigation through default table of content) these documents is time-consuming and challenging. These documents are also authored to be consumed by varied entities (referred to as persona in the paper) interested in only certain parts of the document. In this work, we describe DynamicToC, a dynamic table of content-based navigator, to aid in the task of non-linear, persona-based document consumption. DynamicToC highlights sections of interest in the document as per the aspects relevant to different personas. DynamicToC is augmented with short questions to assist the users in understanding underlying content. This uses a novel deep-reinforcement learning technique to generate questions on these persona-clustered paragraphs. Human and automatic evaluations suggest the efficacy of both end-to-end pipeline and different components of DynamicToC.

Style transfer has been widely explored in natural language generation with non-parallel corpus by directly or indirectly extracting a notion of style from source and target domain corpus. A common shortcoming of existing approaches is the prerequisite of joint annotations across all the stylistic dimensions under consideration. Availability of such dataset across a combination of styles limits the extension of these setups to multiple style dimensions. While cascading single-dimensional models across multiple styles is a possibility, it suffers from content loss, especially when the style dimensions are not completely independent of each other. In our work, we relax this requirement of jointly annotated data across multiple styles by using independently acquired data across different style dimensions without any additional annotations. We initialize an encoder-decoder setup with transformer-based language model pre-trained on a generic corpus and enhance its re-writing capability to multiple target style dimensions by employing multiple style-aware language models as discriminators. Through quantitative and qualitative evaluation, we show the ability of our model to control styles across multiple style dimensions while preserving content of the input text. We compare it against baselines involving cascaded state-of-the-art uni-dimensional style transfer models.