Related papers: Semantic-Based Self-Critical Training For Question…

Natural language processing (NLP) systems are increasingly trained to generate open-ended text rather than classifying between responses. This makes research on evaluation metrics for generated language -- functions that score system output…

We perform neural machine translation of sentence fragments in order to create large amounts of training data for English grammatical error correction. Our method aims at simulating mistakes made by second language learners, and produces a…

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to…

Can language models improve their reasoning performance without external rewards, using only their own sampled responses for training? We show that they can. We propose Self-evolving Post-Training (SePT), a simple post-training method that…

In the realm of education, student evaluation holds equal significance to imparting knowledge. To be evaluated, students usually need to go through text-based academic assessment methods. Instructors need to make a diverse set of questions…

In the last several years, the field of computer assisted language learning has increasingly focused on computer aided question generation. However, this approach often provides test takers with an exhaustive amount of questions that are…

Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability. Specifically, most of the well-performed metrics are required to train on evaluation datasets of…

We present a method for generating training data for reinforcement learning with verifiable rewards to improve small open-weights language models on mathematical tasks. Existing data generation approaches rely on open-loop pipelines and…

Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…

Natural language generation (NLG) systems are commonly evaluated using n-gram overlap measures (e.g. BLEU, ROUGE). These measures do not directly capture semantics or speaker intentions, and so they often turn out to be misaligned with our…

Recently, a human evaluation study of Referring Expression Generation (REG) models had an unexpected conclusion: on \textsc{webnlg}, Referring Expressions (REs) generated by the state-of-the-art neural models were not only indistinguishable…

We propose a two-stage neural model to tackle question generation from documents. First, our model estimates the probability that word sequences in a document are ones that a human would pick when selecting candidate answers by training a…

Over the past two decades, dialogue modeling has made significant strides, moving from simple rule-based responses to personalized and persuasive response generation. However, despite these advancements, the objective functions and…

For a computer to naturally interact with a human, it needs to be human-like. In this paper, we propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. Our model based on…

Generating responses that are consistent with the dialogue context is one of the central challenges in building engaging conversational agents. We demonstrate that neural conversation models can be geared towards generating consistent…

Intelligent and adaptive online education systems aim to make high-quality education available for a diverse range of students. However, existing systems usually depend on a pool of hand-made questions, limiting how fine-grained and…

Retrieval augmented generation mitigates limitations of large language models in factual consistency and knowledge updating by introducing external knowledge. However, practical applications still suffer from semantic misalignment between…

This work aims to employ natural language generation (NLG) to rapidly generate items for English language learning applications: this requires both language models capable of generating fluent, high-quality English, and to control the…

Multiple choice benchmarks have long been the workhorse of language model evaluation because grading multiple choice is objective and easy to automate. However, we show multiple choice questions from popular benchmarks can often be answered…

Large language model (LLM) training faces a critical bottleneck: the scarcity of high-quality, reasoning-intensive question-answer pairs, especially from sparse, domain-specific sources like PubMed papers or legal documents. Existing…