Related papers: You Can Generate It Again: Data-to-Text Generation…

With the recent proliferation of Large Language Models (LLMs), there has been an increasing demand for tools to detect machine-generated text. The effective detection of machine-generated text face two pertinent problems: First, they are…

Recent approaches to data-to-text generation have adopted the very successful encoder-decoder architecture or variants thereof. These models generate text which is fluent (but often imprecise) and perform quite poorly at selecting…

Recent large language models (LLMs) achieve strong performance in generating promising reasoning paths for complex tasks. However, despite powerful generation ability, LLMs remain weak at verifying their own answers, revealing a persistent…

Large-scale pre-trained language models have demonstrated strong capabilities of generating realistic text. However, it remains challenging to control the generation results. Previous approaches such as prompting are far from sufficient,…

While recent Large Vision-Language Models (LVLMs) have shown remarkable performance in multi-modal tasks, they are prone to generating hallucinatory text responses that do not align with the given visual input, which restricts their…

Data-to-text generation focuses on generating fluent natural language responses from structured meaning representations (MRs). Such representations are compositional and it is costly to collect responses for all possible combinations of…

Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…

Sequence-to-sequence models have been applied to the conversation response generation problem where the source sequence is the conversation history and the target sequence is the response. Unlike translation, conversation responding is…

Large pre-trained language models have repeatedly shown their ability to produce fluent text. Yet even when starting from a prompt, generation can continue in many plausible directions. Current decoding methods with the goal of controlling…

Short-reading comprehension questions help students understand text structure but lack effective feedback. Students struggle to identify and correct errors, while manual feedback creation is labor-intensive. This highlights the need for…

We propose an approach for preventing unsafe or otherwise low-quality large language model (LLM) outputs by leveraging the stochasticity of LLMs, an approach we call Repeated Checking with Regeneration (RCR). In this system, LLM checkers…

Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but they typically require altering model architecture or collecting additional data,…

We present a novel approach to automated proof generation for the TLA+ Proof System (TLAPS) using Large Language Models (LLMs). Our method combines two key components: a sub-proof obligation generation phase that breaks down complex proof…

Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…

Large Language Models (LLMs) show promise in automated software engineering, yet their guarantee of correctness is frequently undermined by erroneous or hallucinated code. To enforce model honesty, formal verification requires LLMs to…

Automated feedback generation for introductory programming assignments is useful for programming education. Most works try to generate feedback to correct a student program by comparing its behavior with an instructor's reference program on…

Data-to-text generation systems aim to generate text descriptions based on input data (often represented in the tabular form). A typical system uses huge training samples for learning the correspondence between tables and texts. However,…

We present a method to control a text-to-image generative model to produce training data useful for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a…

Generating coherent, grammatically correct, and meaningful text is very challenging, however, it is crucial to many modern NLP systems. So far, research has mostly focused on English language, for other languages both standardized datasets,…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…