Related papers: Avoidance Decoding for Diverse Multi-Branch Story …

Existing research on large language models (LLMs) shows that they can solve information extraction tasks through multi-step planning. However, their extraction behavior on complex sentences and tasks is unstable, emerging issues such as…

Despite the exceptional performance of multi-modal large language models (MLLMs), their deployment requires substantial computational resources. Once malicious users induce high energy consumption and latency time (energy-latency cost), it…

The rapid advancement of large language models (LLMs) has revolutionized code generation tasks across various programming languages. However, the unique characteristics of programming languages, particularly those like Verilog with specific…

Output diversity is crucial for Large Language Models as it underpins pluralism and creativity. In this work, we reveal that controlling the language used during model thinking-the language of thought-provides a novel and structural source…

Pre-trained models have achieved remarkable success in natural language processing (NLP). However, existing pre-training methods underutilize the benefits of language understanding for generation. Inspired by the idea of Generative…

Decoding strategies manipulate the probability distribution underlying the output of a language model and can therefore affect both generation quality and its uncertainty. In this study, we investigate the impact of decoding strategies on…

The advent of large language models (LLMs) has significantly advanced artificial intelligence (AI) in software engineering (SE), with source code embeddings playing a crucial role in tasks such as source code clone detection and source code…

Diffusion large language models (dLLMs) generate text through iterative denoising. In commonly adopted parallel decoding schemes, each step confirms only high-confidence positions while remasking the others. By analyzing dLLM denoising…

The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has…

Recent advancements in large language models (LLMs) have demonstrated impressive performance in molecular generation, which offers potential to accelerate drug discovery. However, the current LLMs overlook a critical requirement for drug…

Modern generative models still lack human-level creativity, particularly in multi-branch diversity. Prior approaches to address this problem often incur heavy computation or strong dependency on model architecture. Therefore, we introduce…

Despite notable advancements in prompting methods for Large Language Models (LLMs), such as Chain-of-Thought (CoT), existing strategies still suffer from excessive token usage and limited generalisability across diverse reasoning tasks. To…

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

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…

Generating executable code from natural language instructions using Large Language Models (LLMs) poses challenges such as semantic ambiguity and understanding taskspecific contexts. To address these issues, we propose a system called…

Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning. However, the extensive reasoning steps involved can significantly increase computational costs, posing challenges for…

The increasing prevalence of AI-generated content alongside human-written text underscores the need for reliable discrimination methods. To address this challenge, we propose a novel framework with textual embeddings from Pre-trained…

Large language models (LLMs) often fabricate a hallucinatory text. Several methods have been developed to detect such text by semantically comparing it with the multiple versions probabilistically regenerated. However, a significant issue…

We introduce a method to reduce refusal rates of large language models (LLMs) on sensitive content without modifying model weights or prompts. Motivated by the observation that refusals in certain models were often preceded by the specific…

To enhance the quality of generated stories, recent story generation models have been investigating the utilization of higher-level attributes like plots or commonsense knowledge. The application of prompt-based learning with large language…