Meeting summarization has become a critical task since digital encounters have become a common practice. Large language models (LLMs) show great potential in summarization, offering enhanced coherence and context understanding compared to traditional methods. However, they still struggle to maintain relevance and avoid hallucination. We introduce a multi-LLM correction approach for meeting summarization using a two-phase process that mimics the human review process: mistake identification and summary refinement. We release QMSum Mistake, a dataset of 200 automatically generated meeting summaries annotated by humans on nine error types, including structural, omission, and irrelevance errors. Our experiments show that these errors can be identified with high accuracy by an LLM. We transform identified mistakes into actionable feedback to improve the quality of a given summary measured by relevance, informativeness, conciseness, and coherence. This post-hoc refinement effectively improves summary quality by leveraging multiple LLMs to validate output quality. Our multi-LLM approach for meeting summarization shows potential for similar complex text generation tasks requiring robustness, action planning, and discussion towards a goal.
Conformal prediction is a powerful framework for constructing prediction sets with valid coverage guarantees in multi-class classification. However, existing methods often rely on a single score function, which can limit their efficiency and informativeness. We propose a novel approach that combines multiple score functions to improve the performance of conformal predictors by identifying optimal weights that minimize prediction set size. Our theoretical analysis establishes a connection between the weighted score functions and subgraph classes of functions studied in Vapnik-Chervonenkis theory, providing a rigorous mathematical basis for understanding the effectiveness of the proposed method. Experiments demonstrate that our approach consistently outperforms single-score conformal predictors while maintaining valid coverage, offering a principled and data-driven way to enhance the efficiency and practicality of conformal prediction in classification tasks.
Curvilinear object segmentation plays a crucial role across various applications, yet datasets in this domain often suffer from small scale due to the high costs associated with data acquisition and annotation. To address these challenges, this paper introduces a novel approach for expanding curvilinear object segmentation datasets, focusing on enhancing the informativeness of generated data and the consistency between semantic maps and generated images. Our method enriches synthetic data informativeness by generating curvilinear objects through their multiple textual features. By combining textual features from each sample in original dataset, we obtain synthetic images that beyond the original dataset's distribution. This initiative necessitated the creation of the Curvilinear Object Segmentation based on Text Generation (COSTG) dataset. Designed to surpass the limitations of conventional datasets, COSTG incorporates not only standard semantic maps but also some textual descriptions of curvilinear object features. To ensure consistency between synthetic semantic maps and images, we introduce the Semantic Consistency Preserving ControlNet (SCP ControlNet). This involves an adaptation of ControlNet with Spatially-Adaptive Normalization (SPADE), allowing it to preserve semantic information that would typically be washed away in normalization layers. This modification facilitates more accurate semantic image synthesis. Experimental results demonstrate the efficacy of our approach across three types of curvilinear objects (angiography, crack and retina) and six public datasets (CHUAC, XCAD, DCA1, DRIVE, CHASEDB1 and Crack500). The synthetic data generated by our method not only expand the dataset, but also effectively improves the performance of other curvilinear object segmentation models. Source code and dataset are available at \url{https://github.com/tanlei0/COSTG}.
Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences. However, the performance of DPO is sensitive to the fine-tuning of its trade-off parameter $\beta$, as well as to the quality of the preference data. We analyze the impact of $\beta$ and data quality on DPO, uncovering that optimal $\beta$ values vary with the informativeness of pairwise data. Addressing the limitations of static $\beta$ values, we introduce a novel framework that dynamically calibrates $\beta$ at the batch level, informed by data quality considerations. Additionally, our method incorporates $\beta$-guided data filtering to safeguard against the influence of outliers. Through empirical evaluation, we demonstrate that our dynamic $\beta$ adjustment technique significantly improves DPO's performance across a range of models and datasets, offering a more robust and adaptable training paradigm for aligning LLMs with human feedback. The code is available at \url{https://github.com/junkangwu/beta-DPO}.
Since LLMs emerged, more attention has been paid to abstractive long-form summarization, where longer input sequences indicate more information contained. Nevertheless, the automatic evaluation of such summaries remains underexplored. The current evaluation metrics for long-form summarization either use similarity-based metrics like ROUGE and BERTScore or LLM-based metrics using appropriate prompts or pre-defined schema. We argue that the former only relies on similarity and fails to consider informativeness while the latter lacks quantitative analysis of informative richness, and is rather subjective and hard to explain. Current evaluation metrics either use traditional metrics like ROUGE and BERTScore, which rely on surface-level similarity and fail to consider informativeness, or simple LLM-based metrics, which are not robust and easily overwhelmed by the long contexts. In this paper, we propose a new evaluation metric called EVA-Score to extract all information from the given summaries, identify overlapped information based on reference, and calculate the information score. We test EVA-Score on several datasets and the experimental results reveal that EVA-Score shows the highest correlation with humans. We also re-evaluate the performance of LLMs on long-form summarization from the information perspective. The results indicate that responses of LLMs still have a gap with the human-written answers. Moreover, we provide a detailed analysis of the effectiveness of EVA-Score, forecasting future ways to automatically evaluate abstractive long-form summarization.
Hallucinations pose a challenge to the application of large language models (LLMs) thereby motivating the development of metrics to evaluate factual precision. We observe that popular metrics using the Decompose-Then-Verify framework, such as \FActScore, can be manipulated by adding obvious or repetitive subclaims to artificially inflate scores. This observation motivates our new customizable plug-and-play subclaim selection component called Core, which filters down individual subclaims according to their uniqueness and informativeness. We show that many popular factual precision metrics augmented by Core are substantially more robust on a wide range of knowledge domains. We release an evaluation framework supporting easy and modular use of Core and various decomposition strategies, which we recommend adoption by the community. We also release an expansion of the FActScore biography dataset to facilitate further studies of decomposition-based factual precision evaluation.
Many real-world robot learning problems, such as pick-and-place or arriving at a destination, can be seen as a problem of reaching a goal state as soon as possible. These problems, when formulated as episodic reinforcement learning tasks, can easily be specified to align well with our intended goal: -1 reward every time step with termination upon reaching the goal state, called minimum-time tasks. Despite this simplicity, such formulations are often overlooked in favor of dense rewards due to their perceived difficulty and lack of informativeness. Our studies contrast the two reward paradigms, revealing that the minimum-time task specification not only facilitates learning higher-quality policies but can also surpass dense-reward-based policies on their own performance metrics. Crucially, we also identify the goal-hit rate of the initial policy as a robust early indicator for learning success in such sparse feedback settings. Finally, using four distinct real-robotic platforms, we show that it is possible to learn pixel-based policies from scratch within two to three hours using constant negative rewards.
Referring Expression Comprehension (REC) aims to localize the target objects specified by free-form natural language descriptions in images. While state-of-the-art methods achieve impressive performance, they perform a dense perception of images, which incorporates redundant visual regions unrelated to linguistic queries, leading to additional computational overhead. This inspires us to explore a question: can we eliminate linguistic-irrelevant redundant visual regions to improve the efficiency of the model? Existing relevant methods primarily focus on fundamental visual tasks, with limited exploration in vision-language fields. To address this, we propose a coarse-to-fine iterative perception framework, called ScanFormer. It can iteratively exploit the image scale pyramid to extract linguistic-relevant visual patches from top to bottom. In each iteration, irrelevant patches are discarded by our designed informativeness prediction. Furthermore, we propose a patch selection strategy for discarded patches to accelerate inference. Experiments on widely used datasets, namely RefCOCO, RefCOCO+, RefCOCOg, and ReferItGame, verify the effectiveness of our method, which can strike a balance between accuracy and efficiency.
Questions are essential tools for acquiring the necessary information to complete information-seeking tasks. However, large language models (LLMs), especially open-source models, often perform poorly in generating informative questions, as measured by expected information gain (EIG). In this paper, we propose a method to enhance the informativeness of LLM-generated questions in 20-question game dialogues. We sample multiple questions from the same model (LLAMA 2-CHAT 7B) for each game and create pairs of low-EIG and high-EIG questions to apply a Direct Preference Optimization (DPO) algorithm. Our results show that this method produces more effective questions (in terms of EIG), even in domains different from those used to train the DPO model.
In the field of crisis/disaster informatics, social media is increasingly being used for improving situational awareness to inform response and relief efforts. Efficient and accurate text classification tools have been a focal area of investigation in crisis informatics. However, current methods mostly rely on single-label text classification models, which fails to capture different insights embedded in dynamic and multifaceted disaster-related social media data. This study introduces a novel approach to disaster text classification by enhancing a pre-trained Large Language Model (LLM) through instruction fine-tuning targeted for multi-label classification of disaster-related tweets. Our methodology involves creating a comprehensive instruction dataset from disaster-related tweets, which is then used to fine-tune an open-source LLM, thereby embedding it with disaster-specific knowledge. This fine-tuned model can classify multiple aspects of disaster-related information simultaneously, such as the type of event, informativeness, and involvement of human aid, significantly improving the utility of social media data for situational awareness in disasters. The results demonstrate that this approach enhances the categorization of critical information from social media posts, thereby facilitating a more effective deployment for situational awareness during emergencies. This research paves the way for more advanced, adaptable, and robust disaster management tools, leveraging the capabilities of LLMs to improve real-time situational awareness and response strategies in disaster scenarios.
Brain transcriptomics provides insights into the molecular mechanisms by which the brain coordinates its functions and processes. However, existing multimodal methods for predicting Alzheimer's disease (AD) primarily rely on imaging and sometimes genetic data, often neglecting the transcriptomic basis of brain. Furthermore, while striving to integrate complementary information between modalities, most studies overlook the informativeness disparities between modalities. Here, we propose TMM, a trusted multiview multimodal graph attention framework for AD diagnosis, using extensive brain-wide transcriptomics and imaging data. First, we construct view-specific brain regional co-function networks (RRIs) from transcriptomics and multimodal radiomics data to incorporate interaction information from both biomolecular and imaging perspectives. Next, we apply graph attention (GAT) processing to each RRI network to produce graph embeddings and employ cross-modal attention to fuse transcriptomics-derived embedding with each imagingderived embedding. Finally, a novel true-false-harmonized class probability (TFCP) strategy is designed to assess and adaptively adjust the prediction confidence of each modality for AD diagnosis. We evaluate TMM using the AHBA database with brain-wide transcriptomics data and the ADNI database with three imaging modalities (AV45-PET, FDG-PET, and VBM-MRI). The results demonstrate the superiority of our method in identifying AD, EMCI, and LMCI compared to state-of-the-arts. Code and data are available at https://github.com/Yaolab-fantastic/TMM.
As Graph Neural Networks (GNNs) become more pervasive, it becomes paramount to build robust tools for computing explanations of their predictions. A key desideratum is that these explanations are faithful, i.e., that they portray an accurate picture of the GNN's reasoning process. A number of different faithfulness metrics exist, begging the question of what faithfulness is exactly, and what its properties are. We begin by showing that existing metrics are not interchangeable -- i.e., explanations attaining high faithfulness according to one metric may be unfaithful according to others -- and can be systematically insensitive to important properties of the explanation, and suggest how to address these issues. We proceed to show that, surprisingly, optimizing for faithfulness is not always a sensible design goal. Specifically, we show that for injective regular GNN architectures, perfectly faithful explanations are completely uninformative. The situation is different for modular GNNs, such as self-explainable and domain-invariant architectures, where optimizing faithfulness does not compromise informativeness, and is also unexpectedly tied to out-of-distribution generalization.
Recent advances in large language models (LLMs) have led to new summarization strategies, offering an extensive toolkit for extracting important information. However, these approaches are frequently limited by their reliance on isolated sources of data. The amount of information that can be gathered is limited and covers a smaller range of themes, which introduces the possibility of falsified content and limited support for multilingual and multimodal data. The paper proposes a novel approach to summarization that tackles such challenges by utilizing the strength of multiple sources to deliver a more exhaustive and informative understanding of intricate topics. The research progresses beyond conventional, unimodal sources such as text documents and integrates a more diverse range of data, including YouTube playlists, pre-prints, and Wikipedia pages. The aforementioned varied sources are then converted into a unified textual representation, enabling a more holistic analysis. This multifaceted approach to summary generation empowers us to extract pertinent information from a wider array of sources. The primary tenet of this approach is to maximize information gain while minimizing information overlap and maintaining a high level of informativeness, which encourages the generation of highly coherent summaries.
Audio segmentation is a key task for many speech technologies, most of which are based on neural networks, usually considered as black boxes, with high-level performances. However, in many domains, among which health or forensics, there is not only a need for good performance but also for explanations about the output decision. Explanations derived directly from latent representations need to satisfy "good" properties, such as informativeness, compactness, or modularity, to be interpretable. In this article, we propose an explainable-by-design audio segmentation model based on non-negative matrix factorization (NMF) which is a good candidate for the design of interpretable representations. This paper shows that our model reaches good segmentation performances, and presents deep analyses of the latent representation extracted from the non-negative matrix. The proposed approach opens new perspectives toward the evaluation of interpretable representations according to "good" properties.
Compute-efficient training of language models has become an important issue. We consider data pruning for data-efficient training of LLMs. In this work, we consider a data pruning method based on information entropy. We propose that the samples in the training corpus be ranked in terms of their informativeness which we estimate through entropy functions. The key idea is that, less informative samples are likely to contain redundant information, and thus should be pruned first. We use the entropy functions based on the negative log-likelihood and the average inverse word frequency of a sample as a surrogate to measure its informativeness. Experiments reveal that the proposed information-based pruning can improve upon various language modeling and downstream tasks, and enhance the generalization capability of language models.
Deep metric learning (DML) has shown to be effective for content-based image retrieval (CBIR) in remote sensing (RS). Most of DML methods for CBIR rely on a high number of annotated images to accurately learn model parameters of deep neural networks (DNNs). However, gathering such data is time-consuming and costly. To address this, we propose an annotation cost-efficient active learning (ANNEAL) method tailored to DML-driven CBIR in RS. ANNEAL aims to create a small but informative training set made up of similar and dissimilar image pairs to be utilized for accurately learning a metric space. The informativeness of image pairs is evaluated by combining uncertainty and diversity criteria. To assess the uncertainty of image pairs, we introduce two algorithms: 1) metric-guided uncertainty estimation (MGUE); and 2) binary classifier guided uncertainty estimation (BCGUE). MGUE algorithm automatically estimates a threshold value that acts as a boundary between similar and dissimilar image pairs based on the distances in the metric space. The closer the similarity between image pairs is to the estimated threshold value the higher their uncertainty. BCGUE algorithm estimates the uncertainty of the image pairs based on the confidence of the classifier in assigning correct similarity labels. The diversity criterion is assessed through a clustering-based strategy. ANNEAL combines either MGUE or BCGUE algorithm with the clustering-based strategy to select the most informative image pairs, which are then labelled by expert annotators as similar or dissimilar. This way of annotating images significantly reduces the annotation cost compared to annotating images with land-use land-cover class labels. Experimental results on two RS benchmark datasets demonstrate the effectiveness of our method. The code of this work is publicly available at \url{https://git.tu-berlin.de/rsim/anneal_tgrs}.
The deployment of safe and trustworthy machine learning systems, and particularly complex black box neural networks, in real-world applications requires reliable and certified guarantees on their performance. The conformal prediction framework offers such formal guarantees by transforming any point into a set predictor with valid, finite-set, guarantees on the coverage of the true at a chosen level of confidence. Central to this methodology is the notion of the nonconformity score function that assigns to each example a measure of ''strangeness'' in comparison with the previously seen observations. While the coverage guarantees are maintained regardless of the nonconformity measure, the point predictor and the dataset, previous research has shown that the performance of a conformal model, as measured by its efficiency (the average size of the predicted sets) and its informativeness (the proportion of prediction sets that are singletons), is influenced by the choice of the nonconformity score function. The current work introduces the Penalized Inverse Probability (PIP) nonconformity score, and its regularized version RePIP, that allow the joint optimization of both efficiency and informativeness. Through toy examples and empirical results on the task of crop and weed image classification in agricultural robotics, the current work shows how PIP-based conformal classifiers exhibit precisely the desired behavior in comparison with other nonconformity measures and strike a good balance between informativeness and efficiency.
Embedders play a central role in machine learning, projecting any object into numerical representations that can, in turn, be leveraged to perform various downstream tasks. The evaluation of embedding models typically depends on domain-specific empirical approaches utilizing downstream tasks, primarily because of the lack of a standardized framework for comparison. However, acquiring adequately large and representative datasets for conducting these assessments is not always viable and can prove to be prohibitively expensive and time-consuming. In this paper, we present a unified approach to evaluate embedders. First, we establish theoretical foundations for comparing embedding models, drawing upon the concepts of sufficiency and informativeness. We then leverage these concepts to devise a tractable comparison criterion (information sufficiency), leading to a task-agnostic and self-supervised ranking procedure. We demonstrate experimentally that our approach aligns closely with the capability of embedding models to facilitate various downstream tasks in both natural language processing and molecular biology. This effectively offers practitioners a valuable tool for prioritizing model trials.
We study whether individuals can learn the informativeness of their information technology through social learning. As in the classic sequential social learning model, rational agents arrive in order and make decisions based on the past actions of others and their private signals. There is uncertainty regarding the informativeness of the common signal-generating process. We show that learning in this setting is not guaranteed, and depends crucially on the relative tail distributions of private beliefs induced by uninformative and informative signals. We identify the phenomenon of perpetual disagreement as the cause of learning and characterize learning in the canonical Gaussian environment.
One of the principal objectives of Natural Language Processing (NLP) is to generate meaningful representations from text. Improving the informativeness of the representations has led to a tremendous rise in the dimensionality and the memory footprint. It leads to a cascading effect amplifying the complexity of the downstream model by increasing its parameters. The available techniques cannot be applied to cross-modal applications such as text-to-image. To ameliorate these issues, a novel Text-to-Image methodology for generating fixed-length representations through a self-supervised Variational Auto-Encoder (VAE) for semantic evaluation applying transformers (TexIm FAST) has been proposed in this paper. The pictorial representations allow oblivious inference while retaining the linguistic intricacies, and are potent in cross-modal applications. TexIm FAST deals with variable-length sequences and generates fixed-length representations with over 75% reduced memory footprint. It enhances the efficiency of the models for downstream tasks by reducing its parameters. The efficacy of TexIm FAST has been extensively analyzed for the task of Semantic Textual Similarity (STS) upon the MSRPC, CNN/ Daily Mail, and XSum data-sets. The results demonstrate 6% improvement in accuracy compared to the baseline and showcase its exceptional ability to compare disparate length sequences such as a text with its summary.