Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBot-Adversarial Dialogue for Safe Conversational Agents
حوار بوت الخصوم لعوامل المحادثة الآمنة
225
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
ستعلم وكلاء المحادثة المدربون على كوربورا كبيرة غير مبالين في التفاعلات البشرية أنماطا وسلوكيات محاكية فيها، والتي تشمل سلوكا هجوميا أو ساما.نقدم إطارا جديدا للإنسان والحلقة النموذجية لتقييم سمية هذه النماذج، ومقارنة مجموعة متنوعة من الأساليب الحالية في كل من حالات المستخدمين غير المصندين والموديين الذين يعرضون نقاط ضعفهم.ثم نذهب لاقتراح طريقتين روايتين لعوامل المحادثة الآمنة، إما عن طريق التدريب على البيانات من إطار عملنا الجديد للنسب في الحلقة في نظام من مرحلتين، أو "سلامة" في "الخبز"إلى نموذج الولادة نفسه.نجد تقنياتنا الجديدة هي (ط) أكثر أمانا من النماذج الحالية؛في حين أنه (2) الحفاظ على مقاييس قابلية الاستقرار مثل التجذير بالنسبة لشركة Chatbots الحديثة.على النقيض من ذلك، فإننا نعرض مشكلات سلامة خطيرة في الأنظمة القياسية الحالية مثل GPT2، حوالة، و BlenderBot.
Conversational agents trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior. We introduce a new human-and-model-in-the-loop framework for evaluating the toxicity of such models, and compare a variety of existing methods in both the cases of non-adversarial and adversarial users that expose their weaknesses. We then go on to propose two novel methods for safe conversational agents, by either training on data from our new human-and-model-in-the-loop framework in a two-stage system, or ''baking-in'' safety to the generative model itself. We find our new techniques are (i) safer than existing models; while (ii) maintaining usability metrics such as engagingness relative to state-of-the-art chatbots. In contrast, we expose serious safety issues in existing standard systems like GPT2, DialoGPT, and BlenderBot.
References used
https://aclanthology.org/
rate research
Read More
Conversational machine reading (CMR) requires machines to communicate with humans through multi-turn interactions between two salient dialogue states of decision making and question generation processes. In open CMR settings, as the more realistic sc
enario, the retrieved background knowledge would be noisy, which results in severe challenges in the information transmission. Existing studies commonly train independent or pipeline systems for the two subtasks. However, those methods are trivial by using hard-label decisions to activate question generation, which eventually hinders the model performance. In this work, we propose an effective gating strategy by smoothing the two dialogue states in only one decoder and bridge decision making and question generation to provide a richer dialogue state reference. Experiments on the OR-ShARC dataset show the effectiveness of our method, which achieves new state-of-the-art results.
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialo
gue-contextualized passage encodings and better locate knowledge relevant to the conversation. An auxiliary loss captures the history of dialogue-document connections. We demonstrate the effectiveness of our model on two document-grounded conversational datasets and provide analyses showing generalization to unseen documents and long dialogue contexts.
Abstractive conversation summarization has received growing attention while most current state-of-the-art summarization models heavily rely on human-annotated summaries. To reduce the dependence on labeled summaries, in this work, we present a simple
yet effective set of Conversational Data Augmentation (CODA) methods for semi-supervised abstractive conversation summarization, such as random swapping/deletion to perturb the discourse relations inside conversations, dialogue-acts-guided insertion to interrupt the development of conversations, and conditional-generation-based substitution to substitute utterances with their paraphrases generated based on the conversation context. To further utilize unlabeled conversations, we combine CODA with two-stage noisy self-training where we first pre-train the summarization model on unlabeled conversations with pseudo summaries and then fine-tune it on labeled conversations. Experiments conducted on the recent conversation summarization datasets demonstrate the effectiveness of our methods over several state-of-the-art data augmentation baselines.
Turn-level user satisfaction is one of the most important performance metrics for conversational agents. It can be used to monitor the agent's performance and provide insights about defective user experiences. While end-to-end deep learning has shown
promising results, having access to a large number of reliable annotated samples required by these methods remains challenging. In a large-scale conversational system, there is a growing number of newly developed skills, making the traditional data collection, annotation, and modeling process impractical due to the required annotation costs and the turnaround times. In this paper, we suggest a self-supervised contrastive learning approach that leverages the pool of unlabeled data to learn user-agent interactions. We show that the pre-trained models using the self-supervised objective are transferable to the user satisfaction prediction. In addition, we propose a novel few-shot transfer learning approach that ensures better transferability for very small sample sizes. The suggested few-shot method does not require any inner loop optimization process and is scalable to very large datasets and complex models. Based on our experiments using real data from a large-scale commercial system, the suggested approach is able to significantly reduce the required number of annotations, while improving the generalization on unseen skills.
Intelligent agents that are confronted with novel concepts in situated environments will need to ask their human teammates questions to learn about the physical world. To better understand this problem, we need data about asking questions in situated
task-based interactions. To this end, we present the Human-Robot Dialogue Learning (HuRDL) Corpus - a novel dialogue corpus collected in an online interactive virtual environment in which human participants play the role of a robot performing a collaborative tool-organization task. We describe the corpus data and a corresponding annotation scheme to offer insight into the form and content of questions that humans ask to facilitate learning in a situated environment. We provide the corpus as an empirically-grounded resource for improving question generation in situated intelligent agents.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
