Related papers: Flip-Flop Consistency: Unsupervised Training for R…

Mitigating hallucinations in Large Language Models (LLMs) is critical for their reliable deployment. Existing methods typically fine-tune LLMs to abstain from answering questions beyond their knowledge scope. However, these methods often…

Large Language Models (LLMs) can be tasked with scoring texts according to pre-defined criteria and on a defined scale, but there is no recognised optimal prompting strategy for this. This article focuses on the task of LLMs scoring journal…

Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter. We evaluate a 15-model open-weight corpus, with the main reliability analyses focused on 10 instruct models across…

Large language model (LLM) scaling inference is key to unlocking greater performance, and leveraging diversity has proven an effective way to enhance it. Motivated by the observed relationship between solution accuracy and meaningful…

Large language models (LLMs) have become pivotal in recent research. However, during the inference process, LLMs still require substantial resources. In this paper, we propose CliqueParcel, a method designed to improve the efficiency of…

Large Language Models (LLMs) are one of the most promising technologies for the next era of speech generation systems, due to their scalability and in-context learning capabilities. Nevertheless, they suffer from multiple stability issues…

This paper addresses the limitations of large-scale language models in safety alignment and robustness by proposing a fine-tuning method that combines contrastive distillation with noise-robust training. The method freezes the backbone…

Malformed, missing, or boundary-value inputs in microservice APIs can cascade across dependent services, threatening reliability. Robustness testing systematically exercises such inputs to expose server-side failures, but generating…

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is…

Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive self-consistency methods mitigate this issue by adjusting the sampling budget; however, they rely on…

Instruction-tuned large language models (LLMs) employ structured templates, such as role markers and special tokens, to enforce format consistency during inference. However, we identify a critical limitation of such formatting: it induces a…

Calibration is crucial in deep learning applications, especially in fields like healthcare and autonomous driving, where accurate confidence estimates are vital for decision-making. However, deep neural networks often suffer from…

While the inconsistency of LLMs is not a novel topic, prior research has predominantly addressed two types of generative inconsistencies: i) Randomness Inconsistency: running the same LLM multiple trials, yielding varying responses; ii)…

Self-consistency has emerged as a powerful method for improving the accuracy of short answers generated by large language models. As previously defined, it only concerns the accuracy of a final answer parsed from generated text. In this…

Large language models (LLMs) can fluently generate student-like responses, making them attractive as simulated students for training and evaluating AI tutors and human educators. Yet such simulators are typically evaluated by output…

Large Language Models (LLMs) are able to improve their responses when instructed to do so, a capability known as self-correction. When instructions provide only the task's goal without specific details about potential issues in the…

Large language models (LLMs) offer substantial promise for text classification in political science, yet their effectiveness often depends on high-quality prompts and exemplars. To address this, we introduce a three-stage framework that…

Evaluating the quality and variability of text generated by Large Language Models (LLMs) poses a significant, yet unresolved research challenge. Traditional evaluation methods, such as ROUGE and BERTScore, which measure token similarity,…

Scaling training compute, measured in FLOPs, has long been shown to improve the accuracy of large language models, yet training remains resource-intensive. Prior work shows that increasing test-time compute (TTC)-for example through…

Large language models (LLMs) operate in two fundamental learning modes - fine-tuning (FT) and in-context learning (ICL) - raising key questions about which mode yields greater language proficiency and whether they differ in their inductive…