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 framework, we identify three common cases where high rewards are incorrectly assigned to undesirable patterns: noise-induced spurious correlation, naturally occurring spurious correlation, and covariate shift. We show that even though learned metrics achieve high performance on the distribution of the data used to train the reward function, the undesirable patterns may be amplified during RL training of the text generation model. While there has been discussion about reward gaming in the RL or safety community, in this discussion piece, we would like to highlight reward gaming in the natural language generation (NLG) community using concrete conditional text generation examples and discuss potential fixes and areas for future work.

The bulk of work adapting transformer models to open-domain dialogue represents dialogue context as the concatenated set of turns in natural language. However, it is unclear if this is the best approach. In this work, we investigate this question by means of an empirical controlled experiment varying the dialogue context format from text-only formats (all recent utterances, summaries, selected utterances) as well as variants that are more structurally different (triples, AMR). We compare these formats based on fine-tuned model performance on two downstream tasks—knowledge selection and response generation. We find that simply concatenating the utterances works as a strong baseline in most cases, but is outperformed in longer contexts by a hybrid approach of combining a summary of the context with recent utterances. Through empirical analysis, our work highlights the need to examine the format of context representation and offers recommendations on adapting general-purpose language models to dialogue tasks.

Large language models such as GPT-3, GPT4, Claude etc., have advanced the state of the art in several natural language generation tasks such as text summarization and machine translation. However when it comes to open-ended tasks with a focus on creativity such as generating stories, poetry, or various forms of figurative language, these state-of-the-art language models are often found to be inadequate. This tutorial aims to bring awareness of the important and emerging research area of open-domain creative generation, with a focus on language generation while also touching on multi-modal generation (e.g., image captioning, visual metaphors). It targets natural language processing (NLP) and artificial intelligence (AI) researchers as well as creative writing practitioners who are interested in building systems that are capable of emulating as well as augmenting human creativity. In particular, we will review recent studies on creative language generation both at the sentence level as well as longer forms of text. We will provide the audiences with a holistic view of 1) the importance and challenges of building creative language generation systems; 2) how we incorporate content planning, domain knowledge and creativity specific heuristics for different forms of creative language generation such as story, poetry, humor, metaphors etc 3) how can we build better evaluation methods for creative text generation? In particular, how could the recent advancement of AI shape the future workforce for creativity? We will conclude the tutorial by outlining future research directions in this area.

A modular approach has the advantage of being compositional and controllable, comparing to most end-to-end models. In this paper we propose Extract-Select-Rewrite (ESR), a three-phase abstractive sentence summarization method. We decompose summarization into three stages: (i) knowledge extraction, where we extract relation triples from the text using off-the-shelf tools; (ii) content selection, where a subset of triples are selected; and (iii) rewriting, where the selected triple are realized into natural language. Our results demonstrates that ESR is competitive with the best end-to-end models while being more faithful. %than these baseline models. Being modular, ESR’s modules can be trained on separate data which is beneficial in low-resource settings and enhancing the style controllability on text generation.

Machine-in-the-loop writing aims to build models that assist humans to accomplish their writing tasks more effectively. Prior work has found that providing users a machine-written draft or sentence-level continuations has limited success since the generated text tends to deviate from users’ intention. To allow the user to retain control over the content, we train a rewriting model that, when prompted, modifies specified spans of text within the user’s original draft to introduce descriptive and figurative elements in the text. We evaluate the model on its ability to collaborate with humans on the task of creative image captioning. On a user study through Amazon Mechanical Turk, our model is rated to be more helpful by users than a baseline infilling language model. In addition, third-party evaluation shows that users write more descriptive and figurative captions when collaborating with our model compared to completing the task alone. However, the improvement is not uniform across user groups: the model is more helpful to skilled users, which risks widening the gap between skilled and novice users, highlighting a need for careful, user-centric evaluation of interactive systems.

Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of intermediate tasks can heavily affect downstream task performance. In this work, we aim to disentangle the effect of scale and relatedness of tasks in multi-task representation learning. We find that, on average, increasing the scale of multi-task learning, in terms of the number of tasks, indeed results in better learned representations than smaller multi-task setups. However, if the target tasks are known ahead of time, then training on a smaller set of related tasks is competitive to the large-scale multi-task training at a reduced computational cost.

To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to consistently perform well. Our baseline models perform poorly on this task (55.4%) and significantly lag behind human performance (93.5%).

Recent work in training large language models (LLMs) to follow natural language instructions has opened up exciting opportunities for natural language interface design. Building on the prior success of large language models in the realm of computer assisted creativity, in this work, we present CoPoet, a collaborative poetry writing system, with the goal of to study if LLM’s actually improve the quality of the generated content. In contrast to auto-completing a user’s text, CoPoet is controlled by user instructions that specify the attributes of the desired text, such as Write a sentence about ‘love’ or Write a sentence ending in ‘fly’. The core component of our system is a language model fine-tuned on a diverse collection of instructions for poetry writing. Our model is not only competitive to publicly available LLMs trained on instructions (InstructGPT), but also capable of satisfying unseen compositional instructions. A study with 15 qualified crowdworkers shows that users successfully write poems with CoPoet on diverse topics ranging from Monarchy to Climate change, which are preferred by third-party evaluators over poems written without the system.

It is well documented that NLP models learn social biases, but little work has been done on how these biases manifest in model outputs for applied tasks like question answering (QA). We introduce the Bias Benchmark for QA (BBQ), a dataset of question-sets constructed by the authors that highlight attested social biases against people belonging to protected classes along nine social dimensions relevant for U.S. English-speaking contexts. Our task evaluate model responses at two levels: (i) given an under-informative context, we test how strongly responses reflect social biases, and (ii) given an adequately informative context, we test whether the model’s biases override a correct answer choice. We find that models often rely on stereotypes when the context is under-informative, meaning the model’s outputs consistently reproduce harmful biases in this setting. Though models are more accurate when the context provides an informative answer, they still rely on stereotypes and average up to 3.4 percentage points higher accuracy when the correct answer aligns with a social bias than when it conflicts, with this difference widening to over 5 points on examples targeting gender for most models tested.

Unsupervised approaches to extractive summarization usually rely on a notion of sentence importance defined by the semantic similarity between a sentence and the document. We propose new metrics of relevance and redundancy using pointwise mutual information (PMI) between sentences, which can be easily computed by a pre-trained language model. Intuitively, a relevant sentence allows readers to infer the document content (high PMI with the document), and a redundant sentence can be inferred from the summary (high PMI with the summary). We then develop a greedy sentence selection algorithm to maximize relevance and minimize redundancy of extracted sentences. We show that our method outperforms similarity-based methods on datasets in a range of domains including news, medical journal articles, and personal anecdotes.