Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques, which reduce the bits needed for model weights or activations with minimal performance loss, have become popular due to the rise of LLMs. However, most quantization studies use pre-trained LLMs, and the impact of quantization on instruction-tuned LLMs and the relationship between perplexity and benchmark performance of quantized LLMs are not well understood. Evaluation of quantized LLMs is often limited to language modeling and a few classification tasks, leaving their performance on other benchmarks unclear. To address these gaps, we propose a structured evaluation framework consisting of three critical dimensions: (1) knowledge \& capacity, (2) alignment, and (3) efficiency, and conduct extensive experiments across ten diverse benchmarks. Our experimental results indicate that LLMs with 4-bit quantization can retain performance comparable to their non-quantized counterparts, and perplexity can serve as a proxy metric for quantized LLMs on most benchmarks. Furthermore, quantized LLMs with larger parameter scales can outperform smaller LLMs. Despite the memory savings achieved through quantization, it can also slow down the inference speed of LLMs. Consequently, substantial engineering efforts and hardware support are imperative to achieve a balanced optimization of decoding speed and memory consumption in the context of quantized LLMs.

Human label variation arises when annotators assign different labels to the same item for valid reasons, while annotation errors occur when labels are assigned for invalid reasons. These two issues are prevalent in NLP benchmarks, yet existing research has studied them in isolation. To the best of our knowledge, there exists no prior work that focuses on teasing apart error from signal, especially in cases where signal is beyond black-and-white. To fill this gap, we introduce a systematic methodology and a new dataset, VariErr (variation versus error), focusing on the NLI task in English. We propose a 2-round annotation procedure with annotators explaining each label and subsequently judging the validity of label-explanation pairs. VariErr contains 7,732 validity judgments on 1,933 explanations for 500 re-annotated MNLI items. We assess the effectiveness of various automatic error detection (AED) methods and GPTs in uncovering errors versus human label variation. We find that state-of-the-art AED methods significantly underperform GPTs and humans. While GPT-4 is the best system, it still falls short of human performance. Our methodology is applicable beyond NLI, offering fertile ground for future research on error versus plausible variation, which in turn can yield better and more trustworthy NLP systems.

Interpretability research aims to bridge the gap between empirical success and our scientific understanding of the inner workings of large language models (LLMs). However, most existing research focuses on analyzing a single mechanism, such as how models copy or recall factual knowledge. In this work, we propose a formulation of competition of mechanisms, which focuses on the interplay of multiple mechanisms instead of individual mechanisms and traces how one of them becomes dominant in the final prediction. We uncover how and where mechanisms compete within LLMs using two interpretability methods: logit inspection and attention modification. Our findings show traces of the mechanisms and their competition across various model components and reveal attention positions that effectively control the strength of certain mechanisms. Code: https://github.com/francescortu/comp-mech. Data: https://huggingface.co/datasets/francescortu/comp-mech.

Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn't previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if irrelevant texts are retrieved, it may impair model performance. In this paper, we propose Retrieval Augmented Iterative Self-Feedback (RA-ISF), a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model's problem-solving capabilities. Experiments show that our method outperforms existing benchmarks, performing well on models like GPT3.5, Llama2, significantly enhancing factual reasoning capabilities and reducing hallucinations.

The world's first beauty pageant for AI women has finally revealed its shortlist of computer-generated ladies. Out of the 1,500 entrants into the Fanvue World AI Creator Awards, the 10 artificial finalist will battle it out to become the first ever Miss AI. And, with contestants ranging from the red-headed travel influencer Olivia C to Turkish model and astronaut Asena Ilik, competition is sure to be fierce. But, just like any other pageant, it will take more than good looks to win the prize and finalists will also be judged on their technology and social media clout. Fanvue co-founder Will Monange says: 'The awards have shown how engaged creators in the AI space are, and the standard of the shortlist is nothing short of incredible.'

Code Pre-trained Models (CodePTMs) based vulnerability detection have achieved promising results over recent years. However, these models struggle to generalize as they typically learn superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities, resulting in poor performance in real-world scenarios beyond the training instances. To tackle this challenge, we introduce VulLLM, a novel framework that integrates multi-task learning with Large Language Models (LLMs) to effectively mine deep-seated vulnerability features. Specifically, we construct two auxiliary tasks beyond the vulnerability detection task. First, we utilize the vulnerability patches to construct a vulnerability localization task. Second, based on the vulnerability features extracted from patches, we leverage GPT-4 to construct a vulnerability interpretation task. VulLLM innovatively augments vulnerability classification by leveraging generative LLMs to understand complex vulnerability patterns, thus compelling the model to capture the root causes of vulnerabilities rather than overfitting to spurious features of a single task. The experiments conducted on six large datasets demonstrate that VulLLM surpasses seven state-of-the-art models in terms of effectiveness, generalization, and robustness.

The most popular Cross-Document Event Coreference Resolution (CDEC) datasets fail to convey the true difficulty of the task, due to the lack of lexical diversity between coreferring event triggers (words or phrases that refer to an event). Furthermore, there is a dearth of event datasets for figurative language, limiting a crucial avenue of research in event comprehension. We address these two issues by introducing ECB+META, a lexically rich variant of Event Coref Bank Plus (ECB+) for CDEC on symbolic and metaphoric language. We use ChatGPT as a tool for the metaphoric transformation of sentences in the documents of ECB+, then tag the original event triggers in the transformed sentences in a semi-automated manner. In this way, we avoid the re-annotation of expensive coreference links. We present results that show existing methods that work well on ECB+ struggle with ECB+META, thereby paving the way for CDEC research on a much more challenging dataset. Code/data: https://github.com/ahmeshaf/llms_coref

Offline optimization aims to maximize a black-box objective function with a static dataset and has wide applications. In addition to the objective function being black-box and expensive to evaluate, numerous complex real-world problems entail optimizing multiple conflicting objectives, i.e., multi-objective optimization (MOO). Nevertheless, offline MOO has not progressed as much as offline single-objective optimization (SOO), mainly due to the lack of benchmarks like Design-Bench for SOO. To bridge this gap, we propose a first benchmark for offline MOO, covering a range of problems from synthetic to real-world tasks. This benchmark provides tasks, datasets, and open-source examples, which can serve as a foundation for method comparisons and advancements in offline MOO. Furthermore, we analyze how the current related methods can be adapted to offline MOO from four fundamental perspectives, including data, model architecture, learning algorithm, and search algorithm. Empirical results show improvements over the best value of the training set, demonstrating the effectiveness of offline MOO methods. As no particular method stands out significantly, there is still an open challenge in further enhancing the effectiveness of offline MOO. We finally discuss future challenges for offline MOO, with the hope of shedding some light on this emerging field. Our code is available at \url{https://github.com/lamda-bbo/offline-moo}.

Precis: A hybrid deep-learning model combines NFL reflectance and other OCT parameters to improve glaucoma diagnosis. Objective: To investigate if a deep learning model could be used to combine nerve fiber layer (NFL) reflectance and other OCT parameters for glaucoma diagnosis. Patients and Methods: This is a prospective observational study where of 106 normal subjects and 164 perimetric glaucoma (PG) patients. Peripapillary NFL reflectance map, NFL thickness map, optic head analysis of disc, and macular ganglion cell complex thickness were obtained using spectral domain OCT. A hybrid deep learning model combined a fully connected network (FCN) and a convolution neural network (CNN) to develop and combine those OCT maps and parameters to distinguish normal and PG eyes. Two deep learning models were compared based on whether the NFL reflectance map was used as part of the input or not. Results: The hybrid deep learning model with reflectance achieved 0.909 sensitivity at 99% specificity and 0.926 at 95%. The overall accuracy was 0.948 with 0.893 sensitivity and 1.000 specificity, and the AROC was 0.979, which is significantly better than the logistic regression models (p < 0.001). The second best model is the hybrid deep learning model w/o reflectance, which also had significantly higher AROC than logistic regression models (p < 0.001). Logistic regression with reflectance model had slightly higher AROC or sensitivity than the other logistic regression model without reflectance (p = 0.024). Conclusions: Hybrid deep learning model significantly improved the diagnostic accuracy, without or without NFL reflectance. Hybrid deep learning model, combining reflectance/NFL thickness/GCC thickness/ONH parameter, may be a practical model for glaucoma screen purposes.

Despite the widespread adoption of Large language models (LLMs), their remarkable capabilities remain limited to a few high-resource languages. Additionally, many low-resource languages (e.g., African languages) are often evaluated only on basic text classification tasks due to the lack of appropriate or comprehensive benchmarks outside of high-resource languages. In this paper, we introduce IrokoBench--a human-translated benchmark dataset for 16 typologicallydiverse low-resource African languages covering three tasks: natural language inference (AfriXNLI), mathematical reasoning (AfriMGSM), and multi-choice knowledge-based QA (AfriMMLU). We use IrokoBench to evaluate zero-shot, few-shot, and translate-test settings (where test sets are translated into English) across 10 open and four proprietary LLMs. Our evaluation reveals a significant performance gap between high-resource languages (such as English and French) and low-resource African languages. We observe a significant performance gap between open and proprietary models, with the highest performing open model, Aya-101 only at 58% of the best-performing proprietary model GPT-4o performance. Machine translating the test set to English before evaluation helped to close the gap for larger models that are English-centric, like LLaMa 3 70B. These findings suggest that more efforts are needed to develop and adapt LLMs for African languages.