Related papers: Counterfactual Off-Policy Training for Neural Resp…

Counterfactual explanations have been a popular method of post-hoc explainability for a variety of settings in Machine Learning. Such methods focus on explaining classifiers by generating new data points that are similar to a given…

In retrieval-based dialogue systems, a response selection model acts as a ranker to select the most appropriate response among several candidates. However, such selection models tend to rely on context-response content similarity, which…

Fact-based dialogue generation is a task of generating a human-like response based on both dialogue context and factual texts. Various methods were proposed to focus on generating informative words that contain facts effectively. However,…

Open-domain dialog generation is a challenging problem; maximum likelihood training can lead to repetitive outputs, models have difficulty tracking long-term conversational goals, and training on standard movie or online datasets may lead…

In real-world machine learning systems, labels are often derived from user behaviors that the system wishes to encourage. Over time, new models must be trained as new training examples and features become available. However, feedback loops…

Deep learning models exhibit a preference for statistical fitting over logical reasoning. Spurious correlations might be memorized when there exists statistical bias in training data, which severely limits the model performance especially…

Large language models (LLMs) have made remarkable progress in a wide range of natural language understanding and generation tasks. However, their ability to generate counterfactuals has not been examined systematically. To bridge this gap,…

We can consider Counterfactuals as belonging in the domain of Discourse structure and semantics, A core area in Natural Language Understanding and in this paper, we introduce an approach to resolving counterfactual detection as well as the…

Being able to generate informative and coherent dialogue responses is crucial when designing human-like open-domain dialogue systems. Encoder-decoder-based dialogue models tend to produce generic and dull responses during the decoding step…

Post-training Large Language Models requires diverse, high-quality data which is rare and costly to obtain, especially in low resource domains and for multi-turn conversations. Common solutions are crowdsourcing or synthetic generation, but…

Adversarial examples tremendously threaten the availability and integrity of machine learning-based systems. While the feasibility of such attacks has been observed first in the domain of image processing, recent research shows that speech…

Generating qualitative responses has always been a challenge for human-computer dialogue systems. Existing dialogue systems generally derive from either retrieval-based or generative-based approaches, both of which have their own pros and…

We present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that modeling hypothetical answers (to clarification questions) as…

Counterfactual explanations are a common tool to explain artificial intelligence models. For Reinforcement Learning (RL) agents, they answer "Why not?" or "What if?" questions by illustrating what minimal change to a state is needed such…

Moving from limited-domain natural language generation (NLG) to open domain is difficult because the number of semantic input combinations grows exponentially with the number of domains. Therefore, it is important to leverage existing…

Learning-based approaches, such as reinforcement and imitation learning are gaining popularity in decision-making for autonomous driving. However, learned policies often fail to generalize and cannot handle novel situations well. Asking and…

The feedback data of recommender systems are often subject to what was exposed to the users; however, most learning and evaluation methods do not account for the underlying exposure mechanism. We first show in theory that applying…

In this work, we propose an adversarial learning method for reward estimation in reinforcement learning (RL) based task-oriented dialog models. Most of the current RL based task-oriented dialog systems require the access to a reward signal…

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…

Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where…