An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation

Large Language Models (LLMs) have shown exceptional performance across various Data-to-Text Generation (DTG) tasks. However, generating factually consistent text in DTG remains challenging for LLMs. Despite this, in-depth evaluations of LLM factual consistency for DTG remain missing in the current literature. This paper addresses this gap by providing an extensive evaluation of factual consistency in LLMs for DTG. Our evaluation covers five widely used DTG datasets (E2E, ViGGo, WikiTableText, DART, and WebNLG) and five prominent LLM families (T5, BART, OPT, BLOOM, and Llama 2). To ensure a thorough evaluation of factual consistency, we use four state-of-the-art automatic metrics and include essential human assessments. Our extensive evaluations reveals three key findings regarding factual consistency in LLMs for DTG. First, Llama 2 often excels in generating factually consistent text, although smaller models like T5 and BART can achieve strong factual consistency on larger, lexically less-diverse datasets. Second, the average rate of change (AROC) indicates that increasing model size (number of model trainable parameters) generally enhances factual consistency of LLMs in DTG. Third, we observe that source-reference divergence (i.e., when the reference text diverges semantically from the source) typically reduces the factual consistency of LLMs in DTG.

Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation

Data-to-text (D2T) generation aims to generate human-readable text from semi-structured data, such as tables and graphs. The recent success of D2T is largely attributed to advancements in LLMs. Despite the success of LLMs, no research has been conducted to illustrate the impact of model size on the performance of fine-tuned LLMs for D2T tasks. D2T model performance is typically assessed based on three key qualities: \textit{readability} (indicates fluency and coherence), \textit{informativeness} (measures content similarity), and \textit{faithfulness} (assesses consistency of factual information). It is currently uncertain whether increasing the size of LLMs effectively improves performance in D2T tasks across these three qualities. The objective of this study is to investigate the performance of fine-tuned LLMs in D2T tasks in terms of model size. Through extensive comparative analysis, we aim to elucidate both the advantages and limitations of scaling model sizes across five widely used D2T datasets (E2E, ViGGo, WikiTableText, DART, and WebNLG) and twelve state-of-the-art LLMs with varying sizes from five different LLM families (T5, BART, OPT, BLOOM, and Llama 2). To comprehensively cover all the three essential qualities of D2T models, we incorporate six widely recognized automatic metrics -- \textsc{BLEU}, \textsc{METEOR}, \textsc{BERTScore}, \textsc{MoverScore}, \textsc{Parent}, and \textsc{BARTScore}. We also provide an in-depth analysis of LLM performance concerning model size in the presence of source-reference divergence, a critical aspect of D2T tasks. Our investigation reveals that increasing LLM size enhances \textit{readability} and \textit{informativeness} in D2T tasks, but larger (in terms of size) LLMs may sacrifice \textit{faithfulness}. Moreover, small-sized LLMs show more resilience than larger ones when source-reference divergence is present.

Language Models are Crossword Solvers

Crosswords are a form of word puzzle that require a solver to demonstrate a high degree of proficiency in natural language understanding, wordplay, reasoning, and world knowledge, along with adherence to character and length constraints. In this paper we tackle the challenge of solving crosswords with Large Language Models (LLMs). We demonstrate that the current generation of state-of-the art (SoTA) language models show significant competence at deciphering cryptic crossword clues, and outperform previously reported SoTA results by a factor of 2-3 in relevant benchmarks. We also develop a search algorithm that builds off this performance to tackle the problem of solving full crossword grids with LLMs for the very first time, achieving an accuracy of 93\% on New York Times crossword puzzles. Contrary to previous work in this area which concluded that LLMs lag human expert performance significantly, our research suggests this gap is a lot narrower.

LADDER: Revisiting the Cosmic Distance Ladder with Deep Learning Approaches and Exploring its Applications

We investigate the prospect of reconstructing the ``cosmic distance ladder'' of the Universe using a novel deep learning framework called LADDER - Learning Algorithm for Deep Distance Estimation and Reconstruction. LADDER is trained on the apparent magnitude data from the Pantheon Type Ia supernovae compilation, incorporating the full covariance information among data points, to produce predictions along with corresponding errors. After employing several validation tests with a number of deep learning models, we pick LADDER as the best performing one. We then demonstrate applications of our method in the cosmological context, that include serving as a model-independent tool for consistency checks for other datasets like baryon acoustic oscillations, calibration of high-redshift datasets such as gamma ray bursts, use as a model-independent mock catalog generator for future probes, etc. Our analysis advocates for interesting yet cautious consideration of machine learning applications in these contexts.

HCDIR: End-to-end Hate Context Detection, and Intensity Reduction model for online comments

Warning: This paper contains examples of the language that some people may find offensive. Detecting and reducing hateful, abusive, offensive comments is a critical and challenging task on social media. Moreover, few studies aim to mitigate the intensity of hate speech. While studies have shown that context-level semantics are crucial for detecting hateful comments, most of this research focuses on English due to the ample datasets available. In contrast, low-resource languages, like Indian languages, remain under-researched because of limited datasets. Contrary to hate speech detection, hate intensity reduction remains unexplored in high-resource and low-resource languages. In this paper, we propose a novel end-to-end model, HCDIR, for Hate Context Detection, and Hate Intensity Reduction in social media posts. First, we fine-tuned several pre-trained language models to detect hateful comments to ascertain the best-performing hateful comments detection model. Then, we identified the contextual hateful words. Identification of such hateful words is justified through the state-of-the-art explainable learning model, i.e., Integrated Gradient (IG). Lastly, the Masked Language Modeling (MLM) model has been employed to capture domain-specific nuances to reduce hate intensity. We masked the 50\% hateful words of the comments identified as hateful and predicted the alternative words for these masked terms to generate convincing sentences. An optimal replacement for the original hate comments from the feasible sentences is preferred. Extensive experiments have been conducted on several recent datasets using automatic metric-based evaluation (BERTScore) and thorough human evaluation. To enhance the faithfulness in human evaluation, we arranged a group of three human annotators with varied expertise.

ChessVision -- A Dataset for Logically Coherent Multi-label Classification

Starting with early successes in computer vision tasks, deep learning based techniques have since overtaken state of the art approaches in a multitude of domains. However, it has been demonstrated time and again that these techniques fail to capture semantic context and logical constraints, instead often relying on spurious correlations to arrive at the answer. Since application of deep learning techniques to critical scenarios are dependent on adherence to domain specific constraints, several attempts have been made to address this issue. One limitation holding back a thorough exploration of this area, is a lack of suitable datasets which feature a rich set of rules. In order to address this, we present the ChessVision Dataset, consisting of 200,000+ images of annotated chess games in progress, requiring recreation of the game state from its corresponding image. This is accompanied by a curated set of rules which constrains the set of predictions to "reasonable" game states, and are designed to probe key semantic abilities like localization and enumeration. Alongside standard metrics, additional metrics to measure performance with regards to logical consistency is presented. We analyze several popular and state of the art vision models on this task, and show that, although their performance on standard metrics are laudable, they produce a plethora of incoherent results, indicating that this dataset presents a significant challenge for future works.

Pathologist-Like Explanations Unveiled: an Explainable Deep Learning System for White Blood Cell Classification

White blood cells (WBCs) play a crucial role in safeguarding the human body against pathogens and foreign substances. Leveraging the abundance of WBC imaging data and the power of deep learning algorithms, automated WBC analysis has the potential for remarkable accuracy. However, the capability of deep learning models to explain their WBC classification remains largely unexplored. In this study, we introduce HemaX, an explainable deep neural network-based model that produces pathologist-like explanations using five attributes: granularity, cytoplasm color, nucleus shape, size relative to red blood cells, and nucleus to cytoplasm ratio (N:C), along with cell classification, localization, and segmentation. HemaX is trained and evaluated on a novel dataset, LeukoX, comprising 467 blood smear images encompassing ten (10) WBC types. The proposed model achieves impressive results, with an average classification accuracy of 81.08% and a Jaccard index of 89.16% for cell localization. Additionally, HemaX performs well in generating the five explanations with a normalized mean square error of 0.0317 for N:C ratio and over 80% accuracy for the other four attributes. Comprehensive experiments comparing against multiple state-of-the-art models demonstrate that HemaX's classification accuracy remains unaffected by its ability to provide explanations. Moreover, empirical analyses and validation by expert hematologists confirm the faithfulness of explanations predicted by our proposed model.

DOST -- Domain Obedient Self-supervised Training for Multi Label Classification with Noisy Labels

The enormous demand for annotated data brought forth by deep learning techniques has been accompanied by the problem of annotation noise. Although this issue has been widely discussed in machine learning literature, it has been relatively unexplored in the context of "multi-label classification" (MLC) tasks which feature more complicated kinds of noise. Additionally, when the domain in question has certain logical constraints, noisy annotations often exacerbate their violations, making such a system unacceptable to an expert. This paper studies the effect of label noise on domain rule violation incidents in the MLC task, and incorporates domain rules into our learning algorithm to mitigate the effect of noise. We propose the Domain Obedient Self-supervised Training (DOST) paradigm which not only makes deep learning models more aligned to domain rules, but also improves learning performance in key metrics and minimizes the effect of annotation noise. This novel approach uses domain guidance to detect offending annotations and deter rule-violating predictions in a self-supervised manner, thus making it more "data efficient" and domain compliant. Empirical studies, performed over two large scale multi-label classification datasets, demonstrate that our method results in improvement across the board, and often entirely counteracts the effect of noise.

Analyzing Semantic Faithfulness of Language Models via Input Intervention on Conversational Question Answering

Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large version, and investigate how faithful their representations are with respect to the semantic content of texts. We formalize a notion of semantic faithfulness, in which the semantic content of a text should causally figure in a model's inferences in question answering. We then test this notion by observing a model's behavior on answering questions about a story after performing two novel semantic interventions -- deletion intervention and negation intervention. While transformer models achieve high performance on standard question answering tasks, we show that they fail to be semantically faithful once we perform these interventions for a significant number of cases (~50% for deletion intervention, and ~20% drop in accuracy for negation intervention). We then propose an intervention-based training regime that can mitigate the undesirable effects for deletion intervention by a significant margin (from ~50% to ~6%). We analyze the inner-workings of the models to better understand the effectiveness of intervention-based training for deletion intervention. But we show that this training does not attenuate other aspects of semantic unfaithfulness such as the models' inability to deal with negation intervention or to capture the predicate-argument structure of texts. We also test InstructGPT, via prompting, for its ability to handle the two interventions and to capture predicate-argument structure. While InstructGPT models do achieve very high performance on predicate-argument structure task, they fail to respond adequately to our deletion and negation interventions.

Pick-Object-Attack: Type-Specific Adversarial Attack for Object Detection

Many recent studies have shown that deep neural models are vulnerable to adversarial samples: images with imperceptible perturbations, for example, can fool image classifiers. In this paper, we generate adversarial examples for object detection, which entails detecting bounding boxes around multiple objects present in the image and classifying them at the same time, making it a harder task than against image classification. We specifically aim to attack the widely used Faster R-CNN by changing the predicted label for a particular object in an image: where prior work has targeted one specific object (a stop sign), we generalise to arbitrary objects, with the key challenge being the need to change the labels of all bounding boxes for all instances of that object type. To do so, we propose a novel method, named Pick-Object-Attack. Pick-Object-Attack successfully adds perturbations only to bounding boxes for the targeted object, preserving the labels of other detected objects in the image. In terms of perceptibility, the perturbations induced by the method are very small. Furthermore, for the first time, we examine the effect of adversarial attacks on object detection in terms of a downstream task, image captioning; we show that where a method that can modify all object types leads to very obvious changes in captions, the changes from our constrained attack are much less apparent.