Search

This paper explores the efficacy of online versus offline evaluation methods in assessing conversational chatbots, specifically comparing first-party direct interactions with third-party observational assessments. By extending a benchmarking dataset of user dialogs with empathetic chatbots with offline third-party evaluations, we present a systematic comparison between the feedback from online interactions and the more detached offline third-party evaluations. Our results reveal that offline human evaluations fail to capture the subtleties of human-chatbot interactions as effectively as online assessments. In comparison, automated third-party evaluations using a GPT-4 model offer a better approximation of first-party human judgments given detailed instructions. This study highlights the limitations of third-party evaluations in grasping the complexities of user experiences and advocates for the integration of direct interaction feedback in conversational AI evaluation to enhance system development and user satisfaction.

This paper investigates the empathetic responding capabilities of ChatGPT, particularly its latest iteration, GPT-4, in comparison to human-generated responses to a wide range of emotional scenarios, both positive and negative. We employ a rigorous evaluation methodology, involving a between-groups study with 600 participants, to evaluate the level of empathy in responses generated by humans and ChatGPT. ChatGPT is prompted in two distinct ways: a standard approach and one explicitly detailing empathy's cognitive, affective, and compassionate counterparts. Our findings indicate that the average empathy rating of responses generated by ChatGPT exceeds those crafted by humans by approximately 10%. Additionally, instructing ChatGPT to incorporate a clear understanding of empathy in its responses makes the responses align approximately 5 times more closely with the expectations of individuals possessing a high degree of empathy, compared to human responses. The proposed evaluation framework serves as a scalable and adaptable framework to assess the empathetic capabilities of newer and updated versions of large language models, eliminating the need to replicate the current study's results in future research., Comment: 21 pages, 16 figures

As conversational models become increasingly available to the general public, users are engaging with this technology in social interactions. Such unprecedented interaction experiences may pose considerable social and psychological risks to the users unless the technology is properly controlled. This highlights the need for scalable and robust evaluation metrics for conversational chatbots. Existing evaluation metrics aim to automate offline user evaluation and approximate human judgment of pre-curated dialogs. However, they are limited in their ability to capture subjective perceptions of users who actually interact with the bots and might not generalize to real-world settings. To address this limitation, we propose an approach to approximate online human evaluation leveraging large language models (LLMs) from the GPT family. We introduce a new Dialog system Evaluation framework based on Prompting (DEP), which enables a fully automatic evaluation pipeline that replicates live user studies and achieves an impressive correlation with human judgment (up to Pearson r=0.95 on a system level). The DEP approach involves collecting synthetic chat logs of evaluated bots with an LLM in the other-play setting, where the LLM is carefully conditioned to follow a specific scenario. We further explore different prompting approaches to produce evaluation scores with the same LLM. The best performing prompts, which contain few-shot demonstrations and instructions, show outstanding performance on the tested dataset and demonstrate the ability to generalize to other dialog corpora., Comment: accepted to SIGDIAL 2023 (long paper)

As chatbots are becoming increasingly popular, we often wonder what users perceive as natural and socially accepted manners of interacting with them. Some researchers maintain that humans should avoid engaging in emotional conversations with chatbots, while others have started building empathetic chatting machines using the latest deep learning techniques. To understand if chatbots should comprehend and display emotions, we conducted semi-structured interviews with 18 participants. Our analysis revealed their overall enthusiasm towards emotionally aware agents. More importantly, users' intention to accept emotional chatbots seem to hinge on how these agents respond to our specific emotions, rather than just the ability to detect human emotions. Our findings also disclosed the specific application domains where emotionally intelligent technology could improve user experience. To conclude, we summarized a set of emotion interaction patterns that inspire users' intention to adopt such technology as well as guidelines useful for the development of emotionally intelligent chatbots.

Open-domain dialog systems (also known as chatbots) have increasingly drawn attention in natural language processing. Some of the recent work aims at incorporating affect information into sequence-to-sequence neural dialog modeling, making the response emotionally richer, while others use hand-crafted rules to determine the desired emotion response. However, they do not explicitly learn the subtle emotional interactions captured in human dialogs. In this paper, we propose a multi-turn dialog system aimed at learning and generating emotional responses that so far only humans know how to do. Compared with two baseline models, offline experiments show that our method performs the best in perplexity scores. Further human evaluations confirm that our chatbot can keep track of the conversation context and generate emotionally more appropriate responses while performing equally well on grammar., Comment: Accepted to IUI 2020 user2agent workshop

Online labor platforms, such as the Amazon Mechanical Turk, provide an effective framework for eliciting responses to judgment tasks. Previous work has shown that workers respond best to financial incentives, especially to extra bonuses. However, most of the tested incentives involve describing the bonus conditions in formulas instead of plain English. We believe that different incentives given in English (or in qualitative framing) will result in differences in workers' performance, especially when task difficulties vary. In this paper, we report the preliminary results of a crowdsourcing experiment comparing workers' performance using only qualitative framings of financial incentives. Our results demonstrate a significant increase in workers' performance using a specific well-formulated qualitative framing inspired by the Peer Truth Serum. This positive effect is observed only when the difficulty of the task is high, while when the task is easy there is no difference of which incentives to use., Comment: Work-in-Progress Paper in the 4th AAAI Conference on Human Computation and Crowdsourcing (HCOMP 2016)