Large language models (LLMs) powered conversational search systems have already been used by hundreds of millions of people, and are believed to bring many benefits over conventional search. However, while decades of research and public discourse interrogated the risk of search systems in increasing selective exposure and creating echo chambers -- limiting exposure to diverse opinions and leading to opinion polarization, little is known about such a risk of LLM-powered conversational search. We conduct two experiments to investigate: 1) whether and how LLM-powered conversational search increases selective exposure compared to conventional search; 2) whether and how LLMs with opinion biases that either reinforce or challenge the user's view change the effect. Overall, we found that participants engaged in more biased information querying with LLM-powered conversational search, and an opinionated LLM reinforcing their views exacerbated this bias. These results present critical implications for the development of LLMs and conversational search systems, and the policy governing these technologies.
We view large language models (LLMs) as stochastic \emph{language layers} in a network, where the learnable parameters are the natural language \emph{prompts} at each layer. We stack two such layers, feeding the output of one layer to the next. We call the stacked architecture a \emph{Deep Language Network} (DLN). We first show how to effectively perform prompt optimization for a 1-Layer language network (DLN-1). We then show how to train 2-layer DLNs (DLN-2), where two prompts must be learnt. We consider the output of the first layer as a latent variable to marginalize, and devise a variational inference algorithm for joint prompt training. A DLN-2 reaches higher performance than a single layer, sometimes comparable to few-shot GPT-4 even when each LLM in the network is smaller and less powerful. The DLN code is open source: https://github.com/microsoft/deep-language-networks .
The recent development of generative and large language models (LLMs) poses new challenges for model evaluation that the research community and industry are grappling with. While the versatile capabilities of these models ignite excitement, they also inevitably make a leap toward homogenization: powering a wide range of applications with a single, often referred to as ``general-purpose'', model. In this position paper, we argue that model evaluation practices must take on a critical task to cope with the challenges and responsibilities brought by this homogenization: providing valid assessments for whether and how much human needs in downstream use cases can be satisfied by the given model (\textit{socio-technical gap}). By drawing on lessons from the social sciences, human-computer interaction (HCI), and the interdisciplinary field of explainable AI (XAI), we urge the community to develop evaluation methods based on real-world socio-requirements and embrace diverse evaluation methods with an acknowledgment of trade-offs between realism to socio-requirements and pragmatic costs. By mapping HCI and current NLG evaluation methods, we identify opportunities for new evaluation methods for LLMs to narrow the socio-technical gap and pose open questions.
We address the fundamental challenge in Natural Language Generation (NLG) model evaluation, the design and validation of evaluation metrics. Recognizing the limitations of existing metrics and issues with human judgment, we propose using measurement theory, the foundation of test design, as a framework for conceptualizing and evaluating the validity and reliability of NLG evaluation metrics. This approach offers a systematic method for defining "good" metrics, developing robust metrics, and assessing metric performance. In this paper, we introduce core concepts in measurement theory in the context of NLG evaluation and key methods to evaluate the performance of NLG metrics. Through this framework, we aim to promote the design, evaluation, and interpretation of valid and reliable metrics, ultimately contributing to the advancement of robust and effective NLG models in real-world settings.
In this work we examine the ability of language models to generate explicit world models of scientific and common-sense reasoning tasks by framing this as a problem of generating text-based games. To support this, we introduce ByteSized32, a corpus of 32 highly-templated text games written in Python totaling 24k lines of code, each centered around a particular task, and paired with a set of 16 unseen text game specifications for evaluation. We propose a suite of automatic and manual metrics for assessing simulation validity, compliance with task specifications, playability, winnability, and alignment with the physical world. In a single-shot evaluation of GPT-4 on this simulation-as-code-generation task, we find it capable of producing runnable games in 27% of cases, highlighting the difficulty of this challenge task. We discuss areas of future improvement, including GPT-4's apparent capacity to perform well at simulating near canonical task solutions, with performance dropping off as simulations include distractors or deviate from canonical solutions in the action space.
Qualitative analysis of textual contents unpacks rich and valuable information by assigning labels to the data. However, this process is often labor-intensive, particularly when working with large datasets. While recent AI-based tools demonstrate utility, researchers may not have readily available AI resources and expertise, let alone be challenged by the limited generalizability of those task-specific models. In this study, we explored the use of large language models (LLMs) in supporting deductive coding, a major category of qualitative analysis where researchers use pre-determined codebooks to label the data into a fixed set of codes. Instead of training task-specific models, a pre-trained LLM could be used directly for various tasks without fine-tuning through prompt learning. Using a curiosity-driven questions coding task as a case study, we found, by combining GPT-3 with expert-drafted codebooks, our proposed approach achieved fair to substantial agreements with expert-coded results. We lay out challenges and opportunities in using LLMs to support qualitative coding and beyond.
Informed consent is a core cornerstone of ethics in human subject research. Through the informed consent process, participants learn about the study procedure, benefits, risks, and more to make an informed decision. However, recent studies showed that current practices might lead to uninformed decisions and expose participants to unknown risks, especially in online studies. Without the researcher's presence and guidance, online participants must read a lengthy form on their own with no answers to their questions. In this paper, we examined the role of an AI-powered chatbot in improving informed consent online. By comparing the chatbot with form-based interaction, we found the chatbot improved consent form reading, promoted participants' feelings of agency, and closed the power gap between the participant and the researcher. Our exploratory analysis further revealed the altered power dynamic might eventually benefit study response quality. We discussed design implications for creating AI-powered chatbots to offer effective informed consent in broader settings.
Conversational surveys, where an agent asks open-ended questions through natural language interfaces, offer a new way to collect information from people. A good follow-up question in a conversational survey prompts high-quality information and delivers engaging experiences. However, generating high-quality follow-up questions on the fly is a non-trivial task. The agent needs to understand the diverse and complex participant responses, adhere to the survey goal, and generate clear and coherent questions. In this study, we propose a knowledge-driven follow-up question generation framework. The framework combines a knowledge selection module to identify salient topics in participants' responses and a generative model guided by selected knowledge entity-relation pairs. To investigate the effectiveness of the proposed framework, we build a new dataset for open-domain follow-up question generation and present a new set of reference-free evaluation metrics based on Gricean Maxim. Our experiments demonstrate that our framework outperforms a GPT-based baseline in both objective evaluation and human-expert evaluation.
Interview chatbots engage users in a text-based conversation to draw out their views and opinions. It is, however, challenging to build effective interview chatbots that can handle user free-text responses to open-ended questions and deliver engaging user experience. As the first step, we are investigating the feasibility and effectiveness of using publicly available, practical AI technologies to build effective interview chatbots. To demonstrate feasibility, we built a prototype scoped to enable interview chatbots with a subset of active listening skills - the abilities to comprehend a user's input and respond properly. To evaluate the effectiveness of our prototype, we compared the performance of interview chatbots with or without active listening skills on four common interview topics in a live evaluation with 206 users. Our work presents practical design implications for building effective interview chatbots, hybrid chatbot platforms, and empathetic chatbots beyond interview tasks.