Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems

Traditionally, offline datasets have been used to evaluate task-oriented dialogue (TOD) models. These datasets lack context awareness, making them suboptimal benchmarks for conversational systems. In contrast, user-agents, which are context-aware, can simulate the variability and unpredictability of human conversations, making them better alternatives as evaluators. Prior research has utilized large language models (LLMs) to develop user-agents. Our work builds upon this by using LLMs to create user-agents for the evaluation of TOD systems. This involves prompting an LLM, using in-context examples as guidance, and tracking the user-goal state. Our evaluation of diversity and task completion metrics for the user-agents shows improved performance with the use of better prompts. Additionally, we propose methodologies for the automatic evaluation of TOD models within this dynamic framework.

ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents

Large language model (LLM)-based agents have been increasingly used to interact with external environments (e.g., games, APIs, etc.) and solve tasks. However, current frameworks do not enable these agents to work with users and interact with them to align on the details of their tasks and reach user-defined goals; instead, in ambiguous situations, these agents may make decisions based on assumptions. This work introduces ReSpAct (Reason, Speak, and Act), a novel framework that synergistically combines the essential skills for building task-oriented "conversational" agents. ReSpAct addresses this need for agents, expanding on the ReAct approach. The ReSpAct framework enables agents to interpret user instructions, reason about complex tasks, execute appropriate actions, and engage in dynamic dialogue to seek guidance, clarify ambiguities, understand user preferences, resolve problems, and use the intermediate feedback and responses of users to update their plans. We evaluated ReSpAct in environments supporting user interaction, such as task-oriented dialogue (MultiWOZ) and interactive decision-making (AlfWorld, WebShop). ReSpAct is flexible enough to incorporate dynamic user feedback and addresses prevalent issues like error propagation and agents getting stuck in reasoning loops. This results in more interpretable, human-like task-solving trajectories than relying solely on reasoning traces. In two interactive decision-making benchmarks, AlfWorld and WebShop, ReSpAct outperform the strong reasoning-only method ReAct by an absolute success rate of 6% and 4%, respectively. In the task-oriented dialogue benchmark MultiWOZ, ReSpAct improved Inform and Success scores by 5.5% and 3%, respectively.

Simulating User Agents for Embodied Conversational-AI

Embodied agents designed to assist users with tasks must engage in natural language interactions, interpret instructions, execute actions, and communicate effectively to resolve issues. However, collecting large-scale, diverse datasets of situated human-robot dialogues to train and evaluate such agents is expensive, labor-intensive, and time-consuming. To address this challenge, we propose building a large language model (LLM)-based user agent that can simulate user behavior during interactions with an embodied agent in a virtual environment. Given a user goal (e.g., make breakfast), at each time step, the user agent may observe" the robot actions or speak" to either intervene with the robot or answer questions. Such a user agent assists in improving the scalability and efficiency of embodied dialogues dataset generation and is critical for enhancing and evaluating the robot's interaction and task completion ability, as well as for research in reinforcement learning using AI feedback. We evaluate our user agent's ability to generate human-like behaviors by comparing its simulated dialogues with the TEACh dataset. We perform three experiments: zero-shot prompting to predict dialogue acts, few-shot prompting, and fine-tuning on the TEACh training subset. Results show the LLM-based user agent achieves an F-measure of 42% with zero-shot prompting and 43.4% with few-shot prompting in mimicking human speaking behavior. Through fine-tuning, performance in deciding when to speak remained stable, while deciding what to say improved from 51.1% to 62.5%. These findings showcase the feasibility of the proposed approach for assessing and enhancing the effectiveness of robot task completion through natural language communication.

Confidence Estimation for LLM-Based Dialogue State Tracking

Estimation of a model's confidence on its outputs is critical for Conversational AI systems based on large language models (LLMs), especially for reducing hallucination and preventing over-reliance. In this work, we provide an exhaustive exploration of methods, including approaches proposed for open- and closed-weight LLMs, aimed at quantifying and leveraging model uncertainty to improve the reliability of LLM-generated responses, specifically focusing on dialogue state tracking (DST) in task-oriented dialogue systems (TODS). Regardless of the model type, well-calibrated confidence scores are essential to handle uncertainties, thereby improving model performance. We evaluate four methods for estimating confidence scores based on softmax, raw token scores, verbalized confidences, and a combination of these methods, using the area under the curve (AUC) metric to assess calibration, with higher AUC indicating better calibration. We also enhance these with a self-probing mechanism, proposed for closed models. Furthermore, we assess these methods using an open-weight model fine-tuned for the task of DST, achieving superior joint goal accuracy (JGA). Our findings also suggest that fine-tuning open-weight LLMs can result in enhanced AUC performance, indicating better confidence score calibration.

Dialog Flow Induction for Constrainable LLM-Based Chatbots

LLM-driven dialog systems are used in a diverse set of applications, ranging from healthcare to customer service. However, given their generalization capability, it is difficult to ensure that these chatbots stay within the boundaries of the specialized domains, potentially resulting in inaccurate information and irrelevant responses. This paper introduces an unsupervised approach for automatically inducing domain-specific dialog flows that can be used to constrain LLM-based chatbots. We introduce two variants of dialog flow based on the availability of in-domain conversation instances. Through human and automatic evaluation over various dialog domains, we demonstrate that our high-quality data-guided dialog flows achieve better domain coverage, thereby overcoming the need for extensive manual crafting of such flows.

AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model

In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, are more efficient few-shot learners than decoder-only models on various tasks. In particular, we train a 20 billion parameter multilingual seq2seq model called Alexa Teacher Model (AlexaTM 20B) and show that it achieves state-of-the-art (SOTA) performance on 1-shot summarization tasks, outperforming a much larger 540B PaLM decoder model. AlexaTM 20B also achieves SOTA in 1-shot machine translation, especially for low-resource languages, across almost all language pairs supported by the model (Arabic, English, French, German, Hindi, Italian, Japanese, Marathi, Portuguese, Spanish, Tamil, and Telugu) on Flores-101 dataset. We also show in zero-shot setting, AlexaTM 20B outperforms GPT3 (175B) on SuperGLUE and SQuADv2 datasets and provides SOTA performance on multilingual tasks such as XNLI, XCOPA, Paws-X, and XWinograd. Overall, our results present a compelling case for seq2seq models as a powerful alternative to decoder-only models for Large-scale Language Model (LLM) training.

Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems

We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system. Though we train using 70% spoken-form data, our teacher models perform comparably to XLM-R and mT5 when evaluated on the written-form Cross-lingual Natural Language Inference (XNLI) corpus. We perform a second stage of pretraining on our teacher models using in-domain data from our system, improving error rates by 3.86% relative for intent classification and 7.01% relative for slot filling. We find that even a 170M-parameter model distilled from our Stage 2 teacher model has 2.88% better intent classification and 7.69% better slot filling error rates when compared to the 2.3B-parameter teacher trained only on public data (Stage 1), emphasizing the importance of in-domain data for pretraining. When evaluated offline using labeled NLU data, our 17M-parameter Stage 2 distilled model outperforms both XLM-R Base (85M params) and DistillBERT (42M params) by 4.23% to 6.14%, respectively. Finally, we present results from a full virtual assistant experimentation platform, where we find that models trained using our pretraining and distillation pipeline outperform models distilled from 85M-parameter teachers by 3.74%-4.91% on an automatic measurement of full-system user dissatisfaction.

MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages

We present the MASSIVE dataset--Multilingual Amazon Slu resource package (SLURP) for Slot-filling, Intent classification, and Virtual assistant Evaluation. MASSIVE contains 1M realistic, parallel, labeled virtual assistant utterances spanning 51 languages, 18 domains, 60 intents, and 55 slots. MASSIVE was created by tasking professional translators to localize the English-only SLURP dataset into 50 typologically diverse languages from 29 genera. We also present modeling results on XLM-R and mT5, including exact match accuracy, intent classification accuracy, and slot-filling F1 score. We have released our dataset, modeling code, and models publicly.

TEACh: Task-driven Embodied Agents that Chat

Robots operating in human spaces must be able to engage in natural language interaction with people, both understanding and executing instructions, and using conversation to resolve ambiguity and recover from mistakes. To study this, we introduce TEACh, a dataset of over 3,000 human--human, interactive dialogues to complete household tasks in simulation. A Commander with access to oracle information about a task communicates in natural language with a Follower. The Follower navigates through and interacts with the environment to complete tasks varying in complexity from "Make Coffee" to "Prepare Breakfast", asking questions and getting additional information from the Commander. We propose three benchmarks using TEACh to study embodied intelligence challenges, and we evaluate initial models' abilities in dialogue understanding, language grounding, and task execution.

Generative Conversational Networks

Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed data) and then train themselves from that data to perform a given task. We use reinforcement learning to optimize the data generation process where the reward signal is the agent's performance on the task. The task can be any language-related task, from intent detection to full task-oriented conversations. In this work, we show that our approach is able to generalise from seed data and performs well in limited data and limited computation settings, with significant gains for intent detection and slot tagging across multiple datasets: ATIS, TOD, SNIPS, and Restaurants8k. We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data. We also conduct an analysis of the novelty of the generated data and provide generated examples for intent detection, slot tagging, and non-goal oriented conversations.