Interpreting User Requests in the Context of Natural Language Standing Instructions

• URL: http://arxiv.org/abs/2311.09796v2
• Date: Thu, 7 Mar 2024 16:49:07 GMT
• Title: Interpreting User Requests in the Context of Natural Language Standing Instructions
• Authors: Nikita Moghe and Patrick Xia and Jacob Andreas and Jason Eisner and Benjamin Van Durme and Harsh Jhamtani
• Abstract summary: We develop NLSI, a language-to-program dataset consisting of over 2.4K dialogues spanning 17 domains. A key challenge in NLSI is to identify which subset of the standing instructions is applicable to a given dialogue.
• Score: 89.12540932734476
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Users of natural language interfaces, generally powered by Large Language Models (LLMs),often must repeat their preferences each time they make a similar request. We describe an approach to LLM-based dialogue modeling in which persistent user constraints and preferences -- collectively termed standing instructions -- as additional context for such interfaces. For example, when a user states "I'm hungry", a previously expressed preference for Persian food can be automatically added to the LLM prompt, influencing the search for relevant restaurants. We develop NLSI, a language-to-program dataset consisting of over 2.4K dialogues spanning 17 domains, where each dialogue is paired with a user profile (a set of users specific standing instructions) and corresponding structured representations (API calls). A key challenge in NLSI is to identify which subset of the standing instructions is applicable to a given dialogue. NLSI contains diverse phenomena, from simple preferences to interdependent instructions such as triggering a hotel search whenever the user is booking tickets to an event. We conduct experiments on NLSI using prompting with large language models and various retrieval approaches, achieving a maximum of 44.7% exact match on API prediction. Our results demonstrate the challenges in identifying the relevant standing instructions and their interpretation into API calls.

Related papers

• Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests [6.33281463741573]
  Indirect User Requests (IURs) are common in human-human task-oriented dialogue and require world knowledge and pragmatic reasoning from the listener. While large language models (LLMs) can handle these requests effectively, smaller models deployed on virtual assistants often struggle due to resource constraints.
  arXiv  Detail & Related papers  (2024-06-12T01:18:04Z)
• Large Language User Interfaces: Voice Interactive User Interfaces powered by LLMs [5.06113628525842]
  We present a framework that can serve as an intermediary between a user and their user interface (UI) We employ a system that stands upon textual semantic mappings of UI components, in the form of annotations. Our engine can classify the most appropriate application, extract relevant parameters, and subsequently execute precise predictions of the user's expected actions.
  arXiv  Detail & Related papers  (2024-02-07T21:08:49Z)
• Parameter-Efficient Conversational Recommender System as a Language Processing Task [52.47087212618396]
  Conversational recommender systems (CRS) aim to recommend relevant items to users by eliciting user preference through natural language conversation. Prior work often utilizes external knowledge graphs for items' semantic information, a language model for dialogue generation, and a recommendation module for ranking relevant items. In this paper, we represent items in natural language and formulate CRS as a natural language processing task.
  arXiv  Detail & Related papers  (2024-01-25T14:07:34Z)
• Eliciting Human Preferences with Language Models [56.68637202313052]
  Language models (LMs) can be directed to perform target tasks by using labeled examples or natural language prompts. We propose to use *LMs themselves* to guide the task specification process. We study GATE in three domains: email validation, content recommendation, and moral reasoning.
  arXiv  Detail & Related papers  (2023-10-17T21:11:21Z)
• Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs [59.74002011562726]
  We propose a novel linguistic cue-based chain-of-thoughts (textitCue-CoT) to provide a more personalized and engaging response. We build a benchmark with in-depth dialogue questions, consisting of 6 datasets in both Chinese and English. Empirical results demonstrate our proposed textitCue-CoT method outperforms standard prompting methods in terms of both textithelpfulness and textitacceptability on all datasets.
  arXiv  Detail & Related papers  (2023-05-19T16:27:43Z)
• Natural Language Decomposition and Interpretation of Complex Utterances [47.30126929007346]
  We introduce an approach to handle complex-intent-bearing utterances from a user via a process of hierarchical natural language decomposition. Our approach uses a pre-trained language model to decompose a complex utterance into a sequence of simpler natural language steps. Experiments show that the proposed approach enables the interpretation of complex utterances with almost no complex training data.
  arXiv  Detail & Related papers  (2023-05-15T14:35:00Z)
• Dialog2API: Task-Oriented Dialogue with API Description and Example Programs [57.336201096903466]
  We introduce a new paradigm for task-oriented dialogue - Dialog2API - to greatly expand the functionality and provide seamless dialogue experience. The model also manages the dialogue policy and interact with the user through generating appropriate natural language responses. Dialog2API can work with many application scenarios such as software automation and customer service.
  arXiv  Detail & Related papers  (2022-12-20T01:52:46Z)
• Contextual Biasing of Language Models for Speech Recognition in Goal-Oriented Conversational Agents [11.193867567895353]
  Goal-oriented conversational interfaces are designed to accomplish specific tasks. We propose a new architecture that utilizes context embeddings derived from BERT on sample utterances provided during inference time. Our experiments show a word error rate (WER) relative reduction of 7% over non-contextual utterance-level NLM rescorers on goal-oriented audio datasets.
  arXiv  Detail & Related papers  (2021-03-18T15:38:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.