Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models

• URL: http://arxiv.org/abs/2005.13170v1
• Date: Wed, 27 May 2020 05:34:12 GMT
• Title: Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models
• Authors: Haochen Liu, Zhiwei Wang, Tyler Derr and Jiliang Tang
• Abstract summary: We investigate whether we can learn to craft input sentences that result in a black-box neural dialogue model being manipulated. We propose a reinforcement learning based model that can generate such desired inputs automatically. Our work reveals the potential of neural dialogue models to be manipulated, which inspires and opens the door towards developing strategies to defend them.
• Score: 44.952436901380416
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, neural network based dialogue systems have become ubiquitous in our increasingly digitalized society. However, due to their inherent opaqueness, some recently raised concerns about using neural models are starting to be taken seriously. In fact, intentional or unintentional behaviors could lead to a dialogue system to generate inappropriate responses. Thus, in this paper, we investigate whether we can learn to craft input sentences that result in a black-box neural dialogue model being manipulated into having its outputs contain target words or match target sentences. We propose a reinforcement learning based model that can generate such desired inputs automatically. Extensive experiments on a popular well-trained state-of-the-art neural dialogue model show that our method can successfully seek out desired inputs that lead to the target outputs in a considerable portion of cases. Consequently, our work reveals the potential of neural dialogue models to be manipulated, which inspires and opens the door towards developing strategies to defend them.

Related papers

• Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner [51.77263363285369]
  We present an approach called Dialogue Action Tokens that adapts language model agents to plan goal-directed dialogues. The core idea is to treat each utterance as an action, thereby converting dialogues into games where existing approaches such as reinforcement learning can be applied.
  arXiv  Detail & Related papers  (2024-06-17T18:01:32Z)
• Introducing Brain-like Concepts to Embodied Hand-crafted Dialog Management System [1.178527785547223]
  This paper presents a neural behavior engine that allows creation of mixed initiative dialog and action generation based on hand-crafted models using a graphical language. A demonstration of the usability of such brain-like architecture is described through a virtual receptionist application running on a semi-public space.
  arXiv  Detail & Related papers  (2024-06-13T10:54:03Z)
• PK-Chat: Pointer Network Guided Knowledge Driven Generative Dialogue Model [79.64376762489164]
  PK-Chat is a Pointer network guided generative dialogue model, incorporating a unified pretrained language model and a pointer network over knowledge graphs. The words generated by PK-Chat in the dialogue are derived from the prediction of word lists and the direct prediction of the external knowledge graph knowledge. Based on the PK-Chat, a dialogue system is built for academic scenarios in the case of geosciences.
  arXiv  Detail & Related papers  (2023-04-02T18:23:13Z)
• Opportunities and Challenges in Neural Dialog Tutoring [54.07241332881601]
  We rigorously analyze various generative language models on two dialog tutoring datasets for language learning. We find that although current approaches can model tutoring in constrained learning scenarios, they perform poorly in less constrained scenarios. Our human quality evaluation shows that both models and ground-truth annotations exhibit low performance in terms of equitable tutoring.
  arXiv  Detail & Related papers  (2023-01-24T11:00:17Z)
• Improving a sequence-to-sequence nlp model using a reinforcement learning policy algorithm [0.0]
  Current neural network models of dialogue generation show great promise for generating answers for chatty agents. But they are short-sighted in that they predict utterances one at a time while disregarding their impact on future outcomes. This work commemorates a preliminary step toward developing a neural conversational model based on the long-term success of dialogues.
  arXiv  Detail & Related papers  (2022-12-28T22:46:57Z)
• Emotion Recognition in Conversation using Probabilistic Soft Logic [17.62924003652853]
  emotion recognition in conversation (ERC) is a sub-field of emotion recognition that focuses on conversations that contain two or more utterances. We implement our approach in a framework called Probabilistic Soft Logic (PSL), a declarative templating language. PSL provides functionality for the incorporation of results from neural models into PSL models. We compare our method with state-of-the-art purely neural ERC systems, and see almost a 20% improvement.
  arXiv  Detail & Related papers  (2022-07-14T23:59:06Z)
• Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension [48.483910831143724]
  Comprehending a dialogue requires a model to capture diverse kinds of key information in the utterances. We develop a novel narrative-guided pre-training strategy that learns by narrating the key information from a dialogue input.
  arXiv  Detail & Related papers  (2022-03-19T05:20:25Z)
• A Taxonomy of Empathetic Response Intents in Human Social Conversations [1.52292571922932]
  Open-domain conversational agents are becoming increasingly popular in the natural language processing community. One of the challenges is enabling them to converse in an empathetic manner. Current neural response generation methods rely solely on end-to-end learning from large scale conversation data to generate dialogues. Recent work has shown the promise of combining dialogue act/intent modelling and neural response generation.
  arXiv  Detail & Related papers  (2020-12-07T21:56:45Z)
• Probing Neural Dialog Models for Conversational Understanding [21.76744391202041]
  We analyze the internal representations learned by neural open-domain dialog systems. Our results suggest that standard open-domain dialog systems struggle with answering questions. We also find that the dyadic, turn-taking nature of dialog is not fully leveraged by these models.
  arXiv  Detail & Related papers  (2020-06-07T17:32:00Z)
• Knowledge Injection into Dialogue Generation via Language Models [85.65843021510521]
  InjK is a two-stage approach to inject knowledge into a dialogue generation model. First, we train a large-scale language model and query it as textual knowledge. Second, we frame a dialogue generation model to sequentially generate textual knowledge and a corresponding response.
  arXiv  Detail & Related papers  (2020-04-30T07:31:24Z)

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.