The diversity across outputs generated by large language models shapes the perception of their quality and utility. Prompt leaks, templated answer structure, and canned responses across different interactions are readily noticed by people, but there is no standard score to measure this aspect of model behavior. In this work we empirically investigate diversity scores on English texts. We find that computationally efficient compression algorithms capture information similar to what is measured by slow to compute $n$-gram overlap homogeneity scores. Further, a combination of measures -- compression ratios, self-repetition of long $n$-grams and Self-BLEU and BERTScore -- are sufficient to report, as they have low mutual correlation with each other. The applicability of scores extends beyond analysis of generative models; for example, we highlight applications on instruction-tuning datasets and human-produced texts. We release a diversity score package to facilitate research and invite consistency across reports.
Modern instruction-tuned models have become highly capable in text generation tasks such as summarization, and are expected to be released at a steady pace. In practice one may now wish to choose confidently, but with minimal effort, the best performing summarization model when applied to a new domain or purpose. In this work, we empirically investigate the test sample size necessary to select a preferred model in the context of news summarization. Empirical results reveal that comparative evaluation converges quickly for both automatic and human evaluation, with clear preferences for a system emerging from under 100 examples. The human preference data allows us to quantify how well automatic scores can reproduce preference rankings across a variety of downstream summarization tasks. We find that, while automatic metrics are stable at smaller sample sizes, only some automatic metrics are able to moderately predict model win rates according to human preference.
With the advent of large language models (LLMs), there has been growing interest in exploring their potential for medical applications. This research aims to investigate the ability of LLMs, specifically ChatGPT, in the context of pharmacovigilance event extraction, of which the main goal is to identify and extract adverse events or potential therapeutic events from textual medical sources. We conduct extensive experiments to assess the performance of ChatGPT in the pharmacovigilance event extraction task, employing various prompts and demonstration selection strategies. The findings demonstrate that while ChatGPT demonstrates reasonable performance with appropriate demonstration selection strategies, it still falls short compared to fully fine-tuned small models. Additionally, we explore the potential of leveraging ChatGPT for data augmentation. However, our investigation reveals that the inclusion of synthesized data into fine-tuning may lead to a decrease in performance, possibly attributed to noise in the ChatGPT-generated labels. To mitigate this, we explore different filtering strategies and find that, with the proper approach, more stable performance can be achieved, although constant improvement remains elusive.
LLMs can generate factually incorrect statements even when provided access to reference documents. Such errors can be dangerous in high-stakes applications (e.g., document-grounded QA for healthcare or finance). We present GenAudit -- a tool intended to assist fact-checking LLM responses for document-grounded tasks. GenAudit suggests edits to the LLM response by revising or removing claims that are not supported by the reference document, and also presents evidence from the reference for facts that do appear to have support. We train models to execute these tasks, and design an interactive interface to present suggested edits and evidence to users. Comprehensive evaluation by human raters shows that GenAudit can detect errors in 8 different LLM outputs when summarizing documents from diverse domains. To ensure that most errors are flagged by the system, we propose a method that can increase the error recall while minimizing impact on precision. We will release our tool (GenAudit) and fact-checking model for public use.
Many diagnostic errors occur because clinicians cannot easily access relevant information in patient Electronic Health Records (EHRs). In this work we propose a method to use LLMs to identify pieces of evidence in patient EHR data that indicate increased or decreased risk of specific diagnoses; our ultimate aim is to increase access to evidence and reduce diagnostic errors. In particular, we propose a Neural Additive Model to make predictions backed by evidence with individualized risk estimates at time-points where clinicians are still uncertain, aiming to specifically mitigate delays in diagnosis and errors stemming from an incomplete differential. To train such a model, it is necessary to infer temporally fine-grained retrospective labels of eventual "true" diagnoses. We do so with LLMs, to ensure that the input text is from before a confident diagnosis can be made. We use an LLM to retrieve an initial pool of evidence, but then refine this set of evidence according to correlations learned by the model. We conduct an in-depth evaluation of the usefulness of our approach by simulating how it might be used by a clinician to decide between a pre-defined list of differential diagnoses.
Text simplification aims to make technical texts more accessible to laypeople but often results in deletion of information and vagueness. This work proposes InfoLossQA, a framework to characterize and recover simplification-induced information loss in form of question-and-answer (QA) pairs. Building on the theory of Question Under Discussion, the QA pairs are designed to help readers deepen their knowledge of a text. We conduct a range of experiments with this framework. First, we collect a dataset of 1,000 linguist-curated QA pairs derived from 104 LLM simplifications of scientific abstracts of medical studies. Our analyses of this data reveal that information loss occurs frequently, and that the QA pairs give a high-level overview of what information was lost. Second, we devise two methods for this task: end-to-end prompting of open-source and commercial language models, and a natural language inference pipeline. With a novel evaluation framework considering the correctness of QA pairs and their linguistic suitability, our expert evaluation reveals that models struggle to reliably identify information loss and applying similar standards as humans at what constitutes information loss.
Evidence-based medicine aims to improve the quality of healthcare by empowering medical decisions and practices with the best available evidence. The rapid growth of medical evidence, which can be obtained from various sources, poses a challenge in collecting, appraising, and synthesizing the evidential information. Recent advancements in generative AI, exemplified by large language models, hold promise in facilitating the arduous task. However, developing accountable, fair, and inclusive models remains a complicated undertaking. In this perspective, we discuss the trustworthiness of generative AI in the context of automated summarization of medical evidence.
We conjecture that hidden state vectors corresponding to individual input tokens encode information sufficient to accurately predict several tokens ahead. More concretely, in this paper we ask: Given a hidden (internal) representation of a single token at position $t$ in an input, can we reliably anticipate the tokens that will appear at positions $\geq t + 2$? To test this, we measure linear approximation and causal intervention methods in GPT-J-6B to evaluate the degree to which individual hidden states in the network contain signal rich enough to predict future hidden states and, ultimately, token outputs. We find that, at some layers, we can approximate a model's output with more than 48% accuracy with respect to its prediction of subsequent tokens through a single hidden state. Finally we present a "Future Lens" visualization that uses these methods to create a new view of transformer states.
We report the presence of a simple neural mechanism that represents an input-output function as a vector within autoregressive transformer language models (LMs). Using causal mediation analysis on a diverse range of in-context-learning (ICL) tasks, we find that a small number attention heads transport a compact representation of the demonstrated task, which we call a function vector (FV). FVs are robust to changes in context, i.e., they trigger execution of the task on inputs such as zero-shot and natural text settings that do not resemble the ICL contexts from which they are collected. We test FVs across a range of tasks, models, and layers and find strong causal effects across settings in middle layers. We investigate the internal structure of FVs and find while that they often contain information that encodes the output space of the function, this information alone is not sufficient to reconstruct an FV. Finally, we test semantic vector composition in FVs, and find that to some extent they can be summed to create vectors that trigger new complex tasks. Taken together, our findings suggest that LLMs contain internal abstractions of general-purpose functions that can be invoked in a variety of contexts.
Unstructured Electronic Health Record (EHR) data often contains critical information complementary to imaging data that would inform radiologists' diagnoses. However, time constraints and the large volume of notes frequently associated with individual patients renders manual perusal of such data to identify relevant evidence infeasible in practice. Modern Large Language Models (LLMs) provide a flexible means of interacting with unstructured EHR data, and may provide a mechanism to efficiently retrieve and summarize unstructured evidence relevant to a given query. In this work, we propose and evaluate an LLM (Flan-T5 XXL) for this purpose. Specifically, in a zero-shot setting we task the LLM to infer whether a patient has or is at risk of a particular condition; if so, we prompt the model to summarize the supporting evidence. Enlisting radiologists for manual evaluation, we find that this LLM-based approach provides outputs consistently preferred to a standard information retrieval baseline, but we also highlight the key outstanding challenge: LLMs are prone to hallucinating evidence. However, we provide results indicating that model confidence in outputs might indicate when LLMs are hallucinating, potentially providing a means to address this.