Related papers: Recipes for Safety in Open-domain Chatbots
Chatbots have the risk of generating offensive utterances, which must be avoided. Post-deployment, one way for a chatbot to continuously improve is to source utterance/label pairs from feedback by live users. However, among users are…
Recent advances in large language models (LLMs) have led to the development of powerful AI chatbots capable of engaging in natural and human-like conversations. However, these chatbots can be potentially harmful, exhibiting manipulative,…
With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…
We demonstrate that large language models are able to simulate Task Oriented Dialogues in novel domains, provided only with an API implementation and a list of goals. We show these simulations can formulate online, automatic metrics that…
Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we move beyond attacking LLMs and instead examine backdoor…
This study presents a unique framework that applies and extends Solove (2006)'s taxonomy to address privacy concerns in interactions with text-based AI chatbots. As chatbot prevalence grows, concerns about user privacy have heightened.…
Generative AI chatbots have proven surprisingly effective at persuading people to change their beliefs and attitudes in lab settings. However, the practical implications of these findings are not yet clear. In this work, we explore the…
Large pre-trained language models have exhibited unprecedented capabilities in producing high-quality text via prompting techniques. This fact introduces new possibilities for data collection and annotation, particularly in situations where…
Chatbots based on large language models offer cheap conversation practice opportunities for language learners. However, they are hard to control for linguistic forms that correspond to learners' current needs, such as grammar. We control…
Dialogue state modules are a useful component in a task-oriented dialogue system. Traditional methods find dialogue states by manually labeling training corpora, upon which neural models are trained. However, the labeling process can be…
Despite the multi-turn open-domain dialogue systems have attracted more and more attention and made great progress, the existing dialogue systems are still very boring. Nearly all the existing dialogue models only provide a response when…
Empathetic dialogue is an indispensable part of building harmonious social relationships and contributes to the development of a helpful AI. Previous approaches are mainly based on fine small-scale language models. With the advent of…
Evaluation of open-domain dialogue systems is highly challenging and development of better techniques is highlighted time and again as desperately needed. Despite substantial efforts to carry out reliable live evaluation of systems in…
Training dialogue systems often entails dealing with noisy training examples and unexpected user inputs. Despite their prevalence, there currently lacks an accurate survey of dialogue noise, nor is there a clear sense of the impact of each…
This thesis investigates the controllability of deep learning-based, end-to-end, generative dialogue systems in both task-oriented and chit-chat scenarios. In particular, we study the different aspects of controlling generative dialogue…
Progress in natural language generation research has been shaped by the ever-growing size of language models. While large language models pre-trained on web data can generate human-sounding text, they also reproduce social biases and…
Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily adapted to new domains, and require minimal domain engineering. A common criticism of these systems is…
Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…
Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…
Utilizing Large Language Models (LLMs) facilitates the creation of flexible and natural dialogues, a task that has been challenging with traditional rule-based dialogue systems. However, LLMs also have the potential to produce unexpected…