In this work, we explore the use of large language models (LLMs) as interpreters of user utterances within a human-robot language interface. A user interacting with a robot that operates in a physical environment should be able to issue commands that interrupt the robot’s actions, for example, corrections or refinement of the task. This study addresses the context-aware interpretation of user utterances, including those issued while the robot is actively engaged in task execution, exploring whether LLMs, without fine-tuning, can translate user commands into corresponding sequences of robot actions. Using an interactive multimodal interface—combining text and video—for a virtual robot operating in simulated home environments, we collect a dataset of user utterances that guide the robot through various household tasks simultaneously capturing manual interpretation when the automatic one fails. Driven by practical considerations, the collected dataset is used to compare the interpretive performance of GPT models with smaller publicly available alternatives. Our findings reveal that action-interrupting utterances pose challenges for all models. While GPT consistently outperforms the smaller models, interpretation accuracy improves across the board when relevant dynamically selected in-context learning examples are included in the prompt.

We tackle the task of mention detection for pair-programming dialogue, a setting which adds several challenges to the task due to the characteristics of natural dialogue, the dynamic environment of the dialogue task, and the domain-specific vocabulary and structures. We compare recent variants of the Llama and GPT families and explore different prompt and context engineering approaches. While aspects like hesitations and references to read-out code and variable names made the task challenging, GPT 4.1 approximated human performance when we provided few-shot examples similar to the inference text and corrected formatting errors.

This paper introduces a novel method for testing the components of theories of (dialogue) coherence through utterance substitution. The method is described and then applied to Inference Anchoring Theory (IAT) in a large scale experimental study with 933 dialogue snippets and 87 annotators. IAT has been used for substantial corpus annotation and practical applications. To address the aim of finding out if and to what extent two aspects of IAT – illocutionary acts and propositional relations – contribute to dialogue coherence, we designed an experiment for systematically comparing the coherence ratings for several variants of short debate snippets. The comparison is between original human-human debate snippets, snippets generated with an IAT-compliant algorithm and snippets produced with ablated versions of the algorithm. This allows us to systematically compare snippets that have identical underlying structures as well as IAT-deficient structures with each other. We found that propositional relations do impact on dialogue coherence (at a statistically highly significant level) whereas we found no such effect for illocutionary act expression. This result suggests that fine-grained inferential relations impact on dialogue coherence, complementing the higher-level coherence structures of, for instance, Rhetorical Structure Theory.

We take first steps in exploring whether Large Language Models (LLMs) can be adapted to dialogic learning practices, specifically pair programming — LLMs have primarily been implemented as programming assistants, not fully exploiting their dialogic potential. We used new dialogue data from real pair-programming interactions between students, prompting state-of-the-art LLMs to assume the role of a student, when generating a response that continues the real dialogue. We asked human annotators to rate human and AI responses on the criteria through which we operationalise the LLMs’ suitability for educational dialogue: Coherence, Collaborativeness, and whether they appeared human. Results show model differences, with Llama-generated responses being rated similarly to human answers on all three criteria. Thus, for at least one of the models we investigated, the LLM utterance-level response generation appears to be suitable for pair-programming dialogue.

Embodied agents performing complex tasks are susceptible to execution failures, motivating the need for effective failure recovery mechanisms. In this work, we introduce a conditional multi-stage failure recovery framework that employs zero-shot chain prompting. The framework is structured into four error-handling stages, with three operating during task execution and one functioning as a post-execution reflection phase.Our approach utilises the reasoning capabilities of LLMs to analyse execution challenges within their environmental context and devise strategic solutions.We evaluate our method on the TfD benchmark of the TEACH dataset and achieve state-of-the-art performance, outperforming a baseline without error recovery by 11.5% and surpassing the strongest existing model by 19%.

We are interested in the generation of navigation instructions, either in their own right or as training material for robotic navigation task. In this paper, we propose a new approach to navigation instruction generation by framing the problem as an image captioning task using semantic maps as visual input. Conventional approaches employ a sequence of panorama images to generate navigation instructions. Semantic maps abstract away from visual details and fuse the information in multiple panorama images into a single top-down representation, thereby reducing computational complexity to process the input. We present a benchmark dataset for instruction generation using semantic maps, propose an initial model and ask human subjects to manually assess the quality of generated instructions. Our initial investigations show promise in using semantic maps for instruction generation instead of a sequence of panorama images, but there is vast scope for improvement. We release the code for data preparation and model training at https://github.com/chengzu-li/VLGen.

In this paper, we investigate the use of large language models (LLMs) like ChatGPT for document-grounded response generation in the context of information-seeking dialogues. For evaluation, we use the MultiDoc2Dial corpus of task-oriented dialogues in four social service domains previously used in the DialDoc 2022 Shared Task. Information-seeking dialogue turns are grounded in multiple documents providing relevant information. We generate dialogue completion responses by prompting a ChatGPT model, using two methods: Chat-Completion and LlamaIndex. ChatCompletion uses knowledge from ChatGPT model pre-training while LlamaIndex also extracts relevant information from documents. Observing that document-grounded response generation via LLMs cannot be adequately assessed by automatic evaluation metrics as they are significantly more verbose, we perform a human evaluation where annotators rate the output of the shared task winning system, the two ChatGPT variants outputs, and human responses. While both ChatGPT variants are more likely to include information not present in the relevant segments, possibly including a presence of hallucinations, they are rated higher than both the shared task winning system and human responses.

Recent research on argumentative dialogues has focused on persuading people to take some action, changing their stance on the topic of discussion, or winning debates. In this work, we focus on argumentative dialogues that aim to open up (rather than change) people’s minds to help them become more understanding to views that are unfamiliar or in opposition to their own convictions. To this end, we present a dataset of 183 argumentative dialogues about 3 controversial topics: veganism, Brexit and COVID-19 vaccination. The dialogues were collected using the Wizard of Oz approach, where wizards leverage a knowledge-base of arguments to converse with participants. Open-mindedness is measured before and after engaging in the dialogue using a questionnaire from the psychology literature, and success of the dialogue is measured as the change in the participant’s stance towards those who hold opinions different to theirs. We evaluate two dialogue models: a Wikipedia-based and an argument-based model. We show that while both models perform closely in terms of opening up minds, the argument-based model is significantly better on other dialogue properties such as engagement and clarity.

Users of interactive search dialogue systems specify their preferences with natural language utterances. However, a schema-driven system is limited to handling the preferences that correspond to the predefined database content. In this work, we present a methodology for extending a schema-driven interactive search dialogue system with the ability to handle unconstrained user preferences. Using unsupervised semantic similarity metrics and the text snippets associated with the search items, the system identifies suitable items for the user’s unconstrained natural language query. In crowd-sourced evaluation, the users chat with our extended restaurant search system. Based on objective metrics and subjective user ratings, we demonstrate the feasibility of using an unsupervised low latency approach to extend a schema-driven search dialogue system to handle unconstrained user preferences.

We describe the construction of the CODA corpus, a parallel corpus of monologues and expository dialogues. The dialogue part of the corpus consists of expository, i.e., information-delivering rather than dramatic, dialogues written by several acclaimed authors. The monologue part of the corpus is a paraphrase in monologue form of these dialogues by a human annotator. The annotator-written monologue preserves all information present in the original dialogue and does not introduce any new information that is not present in the original dialogue. The corpus was constructed as a resource for extracting rules for automated generation of dialogue from monologue. Using authored dialogues allows us to analyse the techniques used by accomplished writers for presenting information in the form of dialogue. The dialogues are annotated with dialogue acts and the monologues with rhetorical structure. We developed annotation and translation guidelines together with a custom-developed tool for carrying out translation, alignment and annotation of the dialogues. The final parallel CODA corpus consists of 1000 dialogue turns that are tagged with dialogue acts and aligned with monologue that expresses the same information and has been annotated with rhetorical structure relations.