Related papers: On Characterizations for Language Generation: Inte…

The rise of Large Language Models (LLMs) has significantly advanced various applications on software engineering tasks, particularly in code generation. Despite the promising performance, LLMs are prone to generate hallucinations, which…

Hallucination in Large Language Models (LLMs) refers to the generation of content that is not faithful to the input or the real-world facts. This paper provides a rigorous treatment of hallucination in LLMs, including formal definitions and…

Large language models (LLMs) achieve remarkable fluency across linguistic and reasoning tasks but remain systematically prone to hallucination. Prevailing accounts attribute hallucinations to data gaps, limited context, or optimization…

Large Language Models (LLMs) have become powerful, but hallucinations remain a vital obstacle to their trustworthy use. Previous works improved the capability of hallucination detection by measuring uncertainty. But they can not explain the…

Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this consistency in the generation? We investigate this phenomenon through the lens of probability…

Given a finite group with a generating subset there is a well-established notion of length for a group element given in terms of its minimal length expression as a product of elements from the generating set. Recently, certain quantities…

Large Language Models (LLMs) have benefited enormously from scaling, yet these gains are bounded by five fundamental limitations: (1) hallucination, (2) context compression, (3) reasoning degradation, (4) retrieval fragility, and (5)…

Neural natural language generation (NLG) models have recently shown remarkable progress in fluency and coherence. However, existing studies on neural NLG are primarily focused on surface-level realizations with limited emphasis on logical…

Assessing the stability of code generation from large language models (LLMs) is essential for judging their reliability in real-world development. We extend prior "structural-entropy concepts" to the program domain by pairing entropy with…

Large Language Models (LLMs) possess a remarkable capacity to generate persuasive and intelligible language. However, coherence does not equate to truthfulness, as the responses often contain subtle hallucinations. Existing benchmarks are…

Code generation, symbolic math reasoning, and other tasks require LLMs to produce outputs that are both syntactically and semantically correct. Constrained LLM generation is a promising direction to enforce adherence to formal grammar, but…

Generative models have shown impressive capabilities in synthesizing high-quality outputs across various domains. However, a persistent challenge is the occurrence of "hallucinations", where the model produces outputs that are plausible but…

Modern generative and vision-language models (VLMs) are increasingly used in scientific and medical decision support, where predicted probabilities must be both accurate and well calibrated. Despite strong empirical results with moderate…

Word embeddings are computed by a class of techniques within natural language processing (NLP), that create continuous vector representations of words in a language from a large text corpus. The stochastic nature of the training process of…

Addressing the issue of hallucinations in large language models (LLMs) is a critical challenge. As the cognitive mechanisms of hallucination have been related to memory, here we explore hallucination for LLM that is enabled with explicit…

While many capabilities of language models (LMs) improve with increased training budget, the influence of scale on hallucinations is not yet fully understood. Hallucinations come in many forms, and there is no universally accepted…

Language models suffer from various degenerate behaviors. These differ between tasks: machine translation (MT) exhibits length bias, while tasks like story generation exhibit excessive repetition. Recent work has attributed the difference…

Training stability is typically regarded as a prerequisite for reliable optimization in large language models. In this work, we analyze how stabilizing training dynamics affects the induced generation distribution. We show that under…

Every formal grammar defines a language and can in principle be used in three ways: to generate strings (production), to recognize them (parsing), or -- given only examples -- to infer the grammar itself (grammar induction). Generation and…

Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine…