Large language models (LLMs) have demonstrated impressive performance on a number of natural language processing tasks, such as question answering and text summarization. However, their performance on sequence labeling tasks such as intent classification and slot filling (IC-SF), which is a central component in personal assistant systems, lags significantly behind discriminative models. Furthermore, there is a lack of substantive research on the robustness of LLMs to various perturbations in the input prompts. The contributions of this paper are three-fold. First, we show that fine-tuning sufficiently large LLMs can produce IC-SF performance comparable to discriminative models. Next, we systematically analyze the performance deterioration of those fine-tuned models due to three distinct yet relevant types of input perturbations - oronyms, synonyms, and paraphrasing. Finally, we propose an efficient mitigation approach, Prompt Perturbation Consistency Learning (PPCL), which works by regularizing the divergence between losses from clean and perturbed samples. Our experiments demonstrate that PPCL can recover on average 59% and 69% of the performance drop for IC and SF tasks, respectively. Furthermore, PPCL beats the data augmentation approach while using ten times fewer augmented data samples.

As research and deployment of AI grows, the computational burden to support and sustain its progress inevitably does too. To train or fine-tune state-of-the-art models in NLP, computer vision, etc., some form of AI hardware acceleration is virtually a requirement. Recent large language models require considerable resources to train and deploy, resulting in significant energy usage, potential carbon emissions, and massive demand for GPUs and other hardware accelerators. However, this surge carries large implications for energy sustainability at the HPC/datacenter level. In this paper, we study the aggregate effect of power-capping GPUs on GPU temperature and power draw at a research supercomputing center. With the right amount of power-capping, we show significant decreases in both temperature and power draw, reducing power consumption and potentially improving hardware life-span with minimal impact on job performance. While power-capping reduces power draw by design, the aggregate system-wide effect on overall energy consumption is less clear; for instance, if users notice job performance degradation from GPU power-caps, they may request additional GPU-jobs to compensate, negating any energy savings or even worsening energy consumption. To our knowledge, our work is the first to conduct and make available a detailed analysis of the effects of GPU power-capping at the supercomputing scale. We hope our work will inspire HPCs/datacenters to further explore, evaluate, and communicate the impact of power-capping AI hardware accelerators for more sustainable AI.

Prior works on detoxification are scattered in the sense that they do not cover all aspects of detoxification needed in a real-world scenario. Notably, prior works restrict the task of developing detoxification models to only a seen subset of platforms, leaving the question of how the models would perform on unseen platforms unexplored. Additionally, these works do not address non-detoxifiability, a phenomenon whereby the toxic text cannot be detoxified without altering the meaning. We propose GreenLLaMA, the first comprehensive end-to-end detoxification framework, which attempts to alleviate the aforementioned limitations. We first introduce a cross-platform pseudo-parallel corpus applying multi-step data processing and generation strategies leveraging ChatGPT. We then train a suite of detoxification models with our cross-platform corpus. We show that our detoxification models outperform the SoTA model trained with human-annotated parallel corpus. We further introduce explanation to promote transparency and trustworthiness. GreenLLaMA additionally offers a unique paraphrase detector especially dedicated for the detoxification task to tackle the non-detoxifiable cases. Through experimental analysis, we demonstrate the effectiveness of our cross-platform corpus and the robustness of GreenLLaMA against adversarial toxicity.

Advances in large language models (LLMs) provide new opportunities in healthcare for improved patient care, clinical decision-making, and enhancement of physician and administrator workflows. However, the potential of these models importantly depends on their ability to generalize effectively across clinical environments and populations, a challenge often underestimated in early development. To better understand reasons for these challenges and inform mitigation approaches, we evaluated ClinicLLM, an LLM trained on [HOSPITAL]'s clinical notes, analyzing its performance on 30-day all-cause readmission prediction focusing on variability across hospitals and patient characteristics. We found poorer generalization particularly in hospitals with fewer samples, among patients with government and unspecified insurance, the elderly, and those with high comorbidities. To understand reasons for lack of generalization, we investigated sample sizes for fine-tuning, note content (number of words per note), patient characteristics (comorbidity level, age, insurance type, borough), and health system aspects (hospital, all-cause 30-day readmission, and mortality rates). We used descriptive statistics and supervised classification to identify features. We found that, along with sample size, patient age, number of comorbidities, and the number of words in notes are all important factors related to generalization. Finally, we compared local fine-tuning (hospital specific), instance-based augmented fine-tuning and cluster-based fine-tuning for improving generalization. Among these, local fine-tuning proved most effective, increasing AUC by 0.25% to 11.74% (most helpful in settings with limited data). Overall, this study provides new insights for enhancing the deployment of large language models in the societally important domain of healthcare, and improving their performance for broader populations.

Processing and reasoning over long contexts is crucial for many practical applications of Large Language Models (LLMs), such as document comprehension and agent construction. Despite recent strides in making LLMs process contexts with more than 100K tokens, there is currently a lack of a standardized benchmark to evaluate this long-context capability. Existing public benchmarks typically focus on contexts around 10K tokens, limiting the assessment and comparison of LLMs in processing longer contexts. In this paper, we propose $\infty$Bench, the first LLM benchmark featuring an average data length surpassing 100K tokens. $\infty$Bench comprises synthetic and realistic tasks spanning diverse domains, presented in both English and Chinese. The tasks in $\infty$Bench are designed to require well understanding of long dependencies in contexts, and make simply retrieving a limited number of passages from contexts not sufficient for these tasks. In our experiments, based on $\infty$Bench, we evaluate the state-of-the-art proprietary and open-source LLMs tailored for processing long contexts. The results indicate that existing long context LLMs still require significant advancements to effectively process 100K+ context. We further present three intriguing analyses regarding the behavior of LLMs processing long context.

Large Language Models (LLMs) have demonstrated impressive performance on several benchmarks. However, traditional studies do not provide formal guarantees on the performance of LLMs. In this work, we propose a novel certification framework for LLM, QuaCer-C, wherein we formally certify the knowledge-comprehension capabilities of popular LLMs. Our certificates are quantitative - they consist of high-confidence, tight bounds on the probability that the target LLM gives the correct answer on any relevant knowledge comprehension prompt. Our certificates for the Llama, Vicuna, and Mistral LLMs indicate that the knowledge comprehension capability improves with an increase in the number of parameters and that the Mistral model is less performant than the rest in this evaluation.

Large language models (LLMs) offer significant potential as tools to support an expanding range of decision-making tasks. However, given their training on human (created) data, LLMs can inherit both societal biases against protected groups, as well as be subject to cognitive bias. Such human-like bias can impede fair and explainable decisions made with LLM assistance. Our work introduces BiasBuster, a framework designed to uncover, evaluate, and mitigate cognitive bias in LLMs, particularly in high-stakes decision-making tasks. Inspired by prior research in psychology and cognitive sciences, we develop a dataset containing 16,800 prompts to evaluate different cognitive biases (e.g., prompt-induced, sequential, inherent). We test various bias mitigation strategies, amidst proposing a novel method using LLMs to debias their own prompts. Our analysis provides a comprehensive picture on the presence and effects of cognitive bias across different commercial and open-source models. We demonstrate that our self-help debiasing effectively mitigate cognitive bias without having to manually craft examples for each bias type.

While fine-tuning large language models (LLMs) for specific tasks often yields impressive results, it comes at the cost of memory inefficiency due to back-propagation in gradient-based training. Memory-efficient Zeroth-order (MeZO) optimizers, recently proposed to address this issue, only require forward passes during training, making them more memory-friendly. However, the quality of gradient estimates in zeroth order optimization often depends on the data dimensionality, potentially explaining why MeZO still exhibits significant performance drops compared to standard fine-tuning across various tasks. Inspired by the success of Parameter-Efficient Fine-Tuning (PEFT), this paper introduces Sparse MeZO, a novel memory-efficient zeroth-order optimization approach that applies ZO only to a carefully chosen subset of parameters. We propose a simple yet effective parameter selection scheme that yields significant performance gains with Sparse-MeZO. Additionally, we develop a memory-optimized implementation for sparse masking, ensuring the algorithm requires only inference-level memory consumption, allowing Sparse-MeZO to fine-tune LLaMA-30b on a single A100 GPU. Experimental results illustrate that Sparse-MeZO consistently improves both performance and convergence speed over MeZO without any overhead. For example, it achieves a 9\% absolute accuracy improvement and 3.5x speedup over MeZO on the RTE task.

Large language models (LLMs) have emerged as a promising alternative to expensive human evaluations. However, the alignment and coverage of LLM-based evaluations are often limited by the scope and potential bias of the evaluation prompts and criteria. To address this challenge, we propose HD-Eval, a novel framework that iteratively aligns LLM-based evaluators with human preference via Hierarchical Criteria Decomposition. HD-Eval inherits the essence from the evaluation mindset of human experts and enhances the alignment of LLM-based evaluators by decomposing a given evaluation task into finer-grained criteria, aggregating them according to estimated human preferences, pruning insignificant criteria with attribution, and further decomposing significant criteria. By integrating these steps within an iterative alignment training process, we obtain a hierarchical decomposition of criteria that comprehensively captures aspects of natural language at multiple levels of granularity. Implemented as a white box, the human preference-guided aggregator is efficient to train and more explainable than relying solely on prompting, and its independence from model parameters makes it applicable to closed-source LLMs. Extensive experiments on three evaluation domains demonstrate the superiority of HD-Eval in further aligning state-of-the-art evaluators and providing deeper insights into the explanation of evaluation results and the task itself.

The surge in popularity of Large Language Models (LLMs) has opened doors for new approaches to the creation of interactive agents. However, managing the temporal behavior of such agents over the course of an interaction remains challenging. The stateful, long-term horizon and quantitative reasoning required for coherent agent behavior does not fit well into the LLM paradigm. We propose a combination of formal logic-based program synthesis and LLM content generation to create generative agents that adhere to temporal constraints. Our approach uses Temporal Stream Logic (TSL) to generate an automaton that enforces a temporal structure on an agent and leaves the details of each action for a moment in time to an LLM. By using TSL, we are able to augment the generative agent where users have a higher level of guarantees on behavior, better interpretability of the system, and more ability to build agents in a modular way. We evaluate our approach on different tasks involved in creating a coherent interactive agent specialized for various application domains. We found that over all of the tasks, our approach using TSL achieves at least 96% adherence, whereas the pure LLM-based approach demonstrates as low as 14.67% adherence.