Related papers: Guaranteed Generation from Large Language Models
Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning Large Language Models (LLMs) for text generation. In particular, recent LLMs such as ChatGPT and GPT-4 can engage in fluent conversations with users after…
Automated test generation is essential for software quality assurance, with coverage rate serving as a key metric to ensure thorough testing. Recent advancements in Large Language Models (LLMs) have shown promise in improving test…
Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This method addresses common LLM limitations, including outdated information and…
The capacity of Large Language Models (LLMs) to follow complex instructions and generate factually accurate text is critical for their real-world application. However, standard decoding methods often fail to robustly satisfy these…
Aligning language models (LMs) with user intent is becoming increasingly relevant to enhance user experience. This calls for designing methods that can allow users to control the properties of the language that LMs generate, for example,…
Large Language Models (LLMs) excel in various language tasks but they often generate incorrect information, a phenomenon known as "hallucinations". Retrieval-Augmented Generation (RAG) aims to mitigate this by using document retrieval for…
We study language generation in the limit - introduced by Kleinberg and Mullainathan [KM24] - building on classical works of Gold [Gol67] and Angluin [Ang79]. [KM24]'s main result is an algorithm for generating from any countable language…
To ensure that text generated by large language models (LLMs) is in an expected format, constrained decoding proposes to enforce strict formal language constraints during generation. However, as we show in this work, not only do such…
Diffusion Language models (DLMs) are a promising avenue for text generation due to their practical properties on tractable controllable generation. They also have the advantage of not having to predict text autoregressively. However,…
We consider the task of text generation in language models with constraints specified in natural language. To this end, we first create a challenging benchmark Cognac that provides as input to the model a topic with example text, along with…
Retrieval-augmented generation (RAG) appears as a promising method to alleviate the "hallucination" problem in large language models (LLMs), since it can incorporate external traceable resources for response generation. The essence of RAG…
As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed. At the same…
Guard models are a critical component of LLM safety, but their sensitivity to superficial linguistic variations remains a key vulnerability. We show that even meaning-preserving paraphrases can cause large fluctuations in safety scores,…
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…
Discrete diffusion models are a class of generative models that construct sequences by progressively denoising samples from a categorical noise distribution. Beyond their rapidly growing ability to generate coherent natural language, these…
Despite their impressive performance, large language models (LMs) still struggle with reliably generating complex output structures when not finetuned to follow the required output format exactly. To address this issue, grammar-constrained…
Large language models (LLMs) have attracted great attention given their strong performance on a wide range of NLP tasks. In practice, users often expect generated texts to fall within a specific length range, making length controlled…
Large language models (LLMs) inherently display hallucinations since the precision of generated texts cannot be guaranteed purely by the parametric knowledge they include. Although retrieval-augmented generation (RAG) systems enhance the…
LLMs are not generally able to adjust the length of their outputs based on strict length requirements, a capability that would improve their usefulness in applications that require adherence to diverse user and system requirements. We…
Large language models (LLMs) inherently operate over a large generation space, yet conventional usage typically reports the most likely generation (MLG) as a point prediction, which underestimates the model's capability: although the…