Current IR evaluation is based on relevance judgments, created either manually or automatically, with decisions outsourced to Large Language Models (LLMs). We offer an alternative paradigm, that never relies on relevance judgments in any form. Instead, a text is defined as relevant if it contains information that enables the answering of key questions. We use this idea to design the EXAM Answerability Metric to evaluate information retrieval/generation systems for their ability to provide topically relevant information. We envision the role of a human judge to edit and define an exam question bank that will test for the presence of relevant information in text. We support this step by generating an initial set of exam questions. In the next phase, an LLM-based question answering system will automatically grade system responses by tracking which exam questions are answerable with which system responses. We propose two evaluation measures, the recall-oriented EXAM Cover metric, and the precision-oriented EXAM Qrels metric, the latter which can be implemented with trec_eval. This paradigm not only allows for the expansion of the exam question set post-hoc but also facilitates the ongoing evaluation of future information systems, whether they focus on retrieval, generation, or both.
Human face generation and editing represent an essential task in the era of computer vision and the digital world. Recent studies have shown remarkable progress in multi-modal face generation and editing, for instance, using face segmentation to guide image generation. However, it may be challenging for some users to create these conditioning modalities manually. Thus, we introduce M3Face, a unified multi-modal multilingual framework for controllable face generation and editing. This framework enables users to utilize only text input to generate controlling modalities automatically, for instance, semantic segmentation or facial landmarks, and subsequently generate face images. We conduct extensive qualitative and quantitative experiments to showcase our frameworks face generation and editing capabilities. Additionally, we propose the M3CelebA Dataset, a large-scale multi-modal and multilingual face dataset containing high-quality images, semantic segmentations, facial landmarks, and different captions for each image in multiple languages. The code and the dataset will be released upon publication.
Autoregressive decoding makes the inference of Large Language Models (LLMs) time-consuming. In this paper, we reconsider speculative sampling and derive two key observations. Firstly, autoregression at the feature (second-to-top-layer) level is more straightforward than at the token level. Secondly, the inherent uncertainty in feature (second-to-top-layer) level autoregression constrains its performance. Based on these insights, we introduce EAGLE (Extrapolation Algorithm for Greater Language-model Efficiency), a simple yet highly efficient speculative sampling framework. By incorporating a token sequence advanced by one time step, EAGLE effectively resolves the uncertainty, enabling precise second-to-top-layer feature prediction with minimal overhead. We conducted comprehensive evaluations of EAGLE, including all models from the Vicuna and LLaMA2-Chat series, the MoE model Mixtral 8x7B Instruct, and tasks in dialogue, code generation, mathematical reasoning, and instruction following. For LLaMA2-Chat 70B, EAGLE achieved a latency speedup ratio of 2.7x-3.5x, doubled throughput, while maintaining the distribution of the generated text.
Large Language Models (LLMs), exemplified by ChatGPT, have significantly reshaped text generation, particularly in the realm of writing assistance. While ethical considerations underscore the importance of transparently acknowledging LLM use, especially in scientific communication, genuine acknowledgment remains infrequent. A potential avenue to encourage accurate acknowledging of LLM-assisted writing involves employing automated detectors. Our evaluation of four cutting-edge LLM-generated text detectors reveals their suboptimal performance compared to a simple ad-hoc detector designed to identify abrupt writing style changes around the time of LLM proliferation. We contend that the development of specialized detectors exclusively dedicated to LLM-assisted writing detection is necessary. Such detectors could play a crucial role in fostering more authentic recognition of LLM involvement in scientific communication, addressing the current challenges in acknowledgment practices.
Distractors are important in learning evaluation. This paper surveys distractor generation tasks using English multiple-choice question datasets for textual and multimodal contexts. In particular, this paper presents a thorough literature review of the recent studies on distractor generation tasks, discusses multiple choice components and their characteristics, analyzes the related datasets, and summarizes the evaluation metrics of distractor generation. Our investigation reveals that more than half of datasets are human-generated from educational sources in specific domains such as Science and English, which are largely text-based, with a lack of open domain and multimodal datasets.
There is increasing interest in employing large language models (LLMs) as cognitive models. For such purposes, it is central to understand which cognitive properties are well-modeled by LLMs, and which are not. In this work, we study the biases of LLMs in relation to those known in children when solving arithmetic word problems. Surveying the learning science literature, we posit that the problem-solving process can be split into three distinct steps: text comprehension, solution planning and solution execution. We construct tests for each one in order to understand which parts of this process can be faithfully modeled by current state-of-the-art LLMs. We generate a novel set of word problems for each of these tests, using a neuro-symbolic method that enables fine-grained control over the problem features. We find evidence that LLMs, with and without instruction-tuning, exhibit human-like biases in both the text-comprehension and the solution-planning steps of the solving process, but not during the final step which relies on the problem's arithmetic expressions (solution execution).
This paper explores the moral judgment and moral reasoning abilities exhibited by Large Language Models (LLMs) across languages through the Defining Issues Test. It is a well known fact that moral judgment depends on the language in which the question is asked. We extend the work of beyond English, to 5 new languages (Chinese, Hindi, Russian, Spanish and Swahili), and probe three LLMs -- ChatGPT, GPT-4 and Llama2Chat-70B -- that shows substantial multilingual text processing and generation abilities. Our study shows that the moral reasoning ability for all models, as indicated by the post-conventional score, is substantially inferior for Hindi and Swahili, compared to Spanish, Russian, Chinese and English, while there is no clear trend for the performance of the latter four languages. The moral judgments too vary considerably by the language.
In few-shot learning, such as meta-learning, few-shot fine-tuning or in-context learning, the limited number of samples used to train a model have a significant impact on the overall success. Although a large number of sample selection strategies exist, their impact on the performance of few-shot learning is not extensively known, as most of them have been so far evaluated in typical supervised settings only. In this paper, we thoroughly investigate the impact of 20 sample selection strategies on the performance of 5 few-shot learning approaches over 8 image and 6 text datasets. In addition, we propose a new method for automatic combination of sample selection strategies (ACSESS) that leverages the strengths and complementary information of the individual strategies. The experimental results show that our method consistently outperforms the individual selection strategies, as well as the recently proposed method for selecting support examples for in-context learning. We also show a strong modality, dataset and approach dependence for the majority of strategies as well as their dependence on the number of shots - demonstrating that the sample selection strategies play a significant role for lower number of shots, but regresses to random selection at higher number of shots.
Video Text Spotting (VTS) is a fundamental visual task that aims to predict the trajectories and content of texts in a video. Previous works usually conduct local associations and apply IoU-based distance and complex post-processing procedures to boost performance, ignoring the abundant temporal information and the morphological characteristics in VTS. In this paper, we propose a novel Global Video Text Spotting Transformer GloTSFormer to model the tracking problem as global associations and utilize the Gaussian Wasserstein distance to guide the morphological correlation between frames. Our main contributions can be summarized as three folds. 1). We propose a Transformer-based global tracking method GloTSFormer for VTS and associate multiple frames simultaneously. 2). We introduce a Wasserstein distance-based method to conduct positional associations between frames. 3). We conduct extensive experiments on public datasets. On the ICDAR2015 video dataset, GloTSFormer achieves 56.0 MOTA with 4.6 absolute improvement compared with the previous SOTA method and outperforms the previous Transformer-based method by a significant 8.3 MOTA.
Chemical reactivity models are developed to predict chemical reaction outcomes in the form of classification (success/failure) or regression (product yield) tasks. The vast majority of the reported models are trained solely on chemical information such as reactants, products, reagents, and solvents, but not on the details of a synthetic protocol. Herein incorporation of procedural text with the aim to augment the Graphormer reactivity model and improve its accuracy is presented. Two major approaches are used: training an adapter Graphormer model that is provided with a GPT-2-derived latent representation of the text procedure (ReacLLaMA-Adapter) and labeling an unlabeled part of a dataset with the LLaMA 2 model followed by training the Graphormer on an extended dataset (Zero-Shot Labeling ReacLLaMA). Both methodologies enhance the discernment of unpromising reactions, thereby providing more accurate models with improved specificity.