Related papers: Nano: Nested Human-in-the-Loop Reward Learning for…

Diffusion Probabilistic Models (DPMs) have demonstrated substantial promise in image generation tasks but heavily rely on the availability of large amounts of training data. Previous works, like GANs, have tackled the limited data problem…

Existing conversational systems are mostly agent-centric, which assumes the user utterances would closely follow the system ontology (for NLU or dialogue state tracking). However, in real-world scenarios, it is highly desirable that the…

Many localized languages struggle to reap the benefits of recent advancements in character recognition systems due to the lack of substantial amount of labeled training data. This is due to the difficulty in generating large amounts of…

Generative AI has significantly changed industries by enabling text-driven image generation, yet challenges remain in achieving high-resolution outputs that align with fine-grained user preferences. Consequently, multi-round interactions…

This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from the difficulty of generating text according to the given…

Numerous recent techniques for text style transfer characterize their approaches as variants of reinforcement learning and preference optimization. In this work, we consider the relationship between these approaches and a class of…

Current alignment pipelines presume a single, universal notion of desirable behavior. However, human preferences often diverge across users, contexts, and cultures. As a result, disagreement collapses into the majority signal and minority…

Much research in recent years has focused on automatic article commenting. However, few of previous studies focus on the controllable generation of comments. Besides, they tend to generate dull and commonplace comments, which further limits…

While developments in machine learning led to impressive performance gains on big data, many human subjects data are, in actuality, small and sparsely labeled. Existing methods applied to such data often do not easily generalize to…

We develop a learning-based algorithm for the distributed formation control of networked multi-agent systems governed by unknown, nonlinear dynamics. Most existing algorithms either assume certain parametric forms for the unknown dynamic…

Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To…

Few-shot learning benchmarks are critical for evaluating modern NLP techniques. It is possible, however, that benchmarks favor methods which easily make use of unlabeled text, because researchers can use unlabeled text from the test set to…

Many text generation tasks naturally contain two steps: content selection and surface realization. Current neural encoder-decoder models conflate both steps into a black-box architecture. As a result, the content to be described in the text…

Paraphrase generation is a longstanding NLP task that has diverse applications for downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised…

We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive learning from language assumes a particular form of input (e.g.,…

Generative models of language exhibit impressive capabilities but still place non-negligible probability mass over undesirable outputs. In this work, we address the task of updating a model to avoid unwanted outputs while minimally changing…

To align conditional text generation model outputs with desired behaviors, there has been an increasing focus on training the model using reinforcement learning (RL) with reward functions learned from human annotations. Under this…

Few-shot learning is a technique to learn a model with a very small amount of labeled training data by transferring knowledge from relevant tasks. In this paper, we propose a few-shot learning method for wearable sensor based human activity…

As language models have a greater impact on society, it is important to ensure they are aligned to a diverse range of perspectives and are able to reflect nuance in human values. However, the most popular training paradigms for modern…

Integrating human expertise into machine learning systems often reduces the role of experts to labeling oracles, a paradigm that limits the amount of information exchanged and fails to capture the nuances of human judgment. We address this…