Implementation and Application of an Intelligibility Protocol for Interaction with an LLM

• URL: http://arxiv.org/abs/2410.20600v1
• Date: Sun, 27 Oct 2024 21:20:18 GMT
• Title: Implementation and Application of an Intelligibility Protocol for Interaction with an LLM
• Authors: Ashwin Srinivasan, Karan Bania, Shreyas V, Harshvardhan Mestha, Sidong Liu,
• Abstract summary: Our interest is in constructing interactive systems involving a human-expert interacting with a machine learning engine. This is of relevance when addressing complex problems arising in areas of science, the environment, medicine and so on. We present an algorithmic description of general-purpose implementation, and conduct preliminary experiments on its use in two different areas.
• Score: 0.9187505256430948
• License:
• Abstract: Our interest is in constructing interactive systems involving a human-expert interacting with a machine learning engine on data analysis tasks. This is of relevance when addressing complex problems arising in areas of science, the environment, medicine and so on, which are not immediately amenable to the usual methods of statistical or mathematical modelling. In such situations, it is possible that harnessing human expertise and creativity to modern machine-learning capabilities of identifying patterns by constructing new internal representations of the data may provide some insight to possible solutions. In this paper, we examine the implementation of an abstract protocol developed for interaction between agents, each capable of constructing predictions and explanations. The \PXP protocol, described in [12] is motivated by the notion of ''two-way intelligibility'' and is specified using a pair of communicating finite-state machines. While the formalisation allows the authors to prove several properties about the protocol, no implementation was presented. Here, we address this shortcoming for the case in which one of the agents acts as a ''generator'' using a large language model (LLM) and the other is an agent that acts as a ''tester'' using either a human-expert, or a proxy for a human-expert (for example, a database compiled using human-expertise). We believe these use-cases will be a widely applicable form of interaction for problems of the kind mentioned above. We present an algorithmic description of general-purpose implementation, and conduct preliminary experiments on its use in two different areas (radiology and drug-discovery). The experimental results provide early evidence in support of the protocol's capability of capturing one- and two-way intelligibility in human-LLM in the manner proposed in [12].

Related papers

• A Multimodal Automated Interpretability Agent [63.8551718480664]
  MAIA is a system that uses neural models to automate neural model understanding tasks. We first characterize MAIA's ability to describe (neuron-level) features in learned representations of images. We then show that MAIA can aid in two additional interpretability tasks: reducing sensitivity to spurious features, and automatically identifying inputs likely to be mis-classified.
  arXiv  Detail & Related papers  (2024-04-22T17:55:11Z)
• Understanding Your Agent: Leveraging Large Language Models for Behavior Explanation [7.647395374489533]
  We propose an approach to generate natural language explanations for an agent's behavior based only on observations of states and actions. We show that our approach generates explanations as helpful as those produced by a human domain expert.
  arXiv  Detail & Related papers  (2023-11-29T20:16:23Z)
• Explaining Agent Behavior with Large Language Models [7.128139268426959]
  We propose an approach to generate natural language explanations for an agent's behavior based only on observations of states and actions. We show how a compact representation of the agent's behavior can be learned and used to produce plausible explanations.
  arXiv  Detail & Related papers  (2023-09-19T06:13:24Z)
• FIND: A Function Description Benchmark for Evaluating Interpretability Methods [86.80718559904854]
  This paper introduces FIND (Function INterpretation and Description), a benchmark suite for evaluating automated interpretability methods. FIND contains functions that resemble components of trained neural networks, and accompanying descriptions of the kind we seek to generate. We evaluate methods that use pretrained language models to produce descriptions of function behavior in natural language and code.
  arXiv  Detail & Related papers  (2023-09-07T17:47:26Z)
• A Model for Intelligible Interaction Between Agents That Predict and Explain [1.335664823620186]
  We formalise the interaction model by taking agents to be automata with some special characteristics. We define One- and Two-Way Intelligibility as properties that emerge at run-time by execution of the protocol. We demonstrate using the formal model to: (a) identify instances of One- and Two-Way Intelligibility in literature reports on humans interacting with ML systems providing logic-based explanations, as is done in Inductive Logic Programming (ILP); and (b) map interactions between humans and machines in an elaborate natural-language based dialogue-model to One- or Two-Way Intellig
  arXiv  Detail & Related papers  (2023-01-04T20:48:22Z)
• DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations [119.1953397679783]
  We focus on advancing the state-of-the-art in interpreting multimodal models. Our proposed approach, DIME, enables accurate and fine-grained analysis of multimodal models.
  arXiv  Detail & Related papers  (2022-03-03T20:52:47Z)
• Multi-Agent Imitation Learning with Copulas [102.27052968901894]
  Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents.
  arXiv  Detail & Related papers  (2021-07-10T03:49:41Z)
• Challenging common interpretability assumptions in feature attribution explanations [0.0]
  We empirically evaluate the veracity of three common interpretability assumptions through a large scale human-subjects experiment. We find that feature attribution explanations provide marginal utility in our task for a human decision maker.
  arXiv  Detail & Related papers  (2020-12-04T17:57:26Z)
• Investigating Human Response, Behaviour, and Preference in Joint-Task Interaction [3.774610219328564]
  We have designed an experiment in order to examine human behaviour and response as they interact with Explainable Planning (XAIP) agents. We also present the results from an empirical analysis where we examined the behaviour of the two agents for simulated users.
  arXiv  Detail & Related papers  (2020-11-27T22:16:59Z)
• DRG: Dual Relation Graph for Human-Object Interaction Detection [65.50707710054141]
  We tackle the challenging problem of human-object interaction (HOI) detection. Existing methods either recognize the interaction of each human-object pair in isolation or perform joint inference based on complex appearance-based features. In this paper, we leverage an abstract spatial-semantic representation to describe each human-object pair and aggregate the contextual information of the scene via a dual relation graph.
  arXiv  Detail & Related papers  (2020-08-26T17:59:40Z)
• A general framework for scientifically inspired explanations in AI [76.48625630211943]
  We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
  arXiv  Detail & Related papers  (2020-03-02T10:32:21Z)

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.