Abstract

Large Language Models (LLMs) often inherit biases from the web data they are trained on, which contains stereotypes and prejudices. Current methods for evaluating and mitigating these biases rely on bias-benchmark datasets. These benchmarks measure bias by observing an LLM’s behavior on biased statements. However, these statements lack contextual considerations of the situations they try to present. To address this, we introduce a contextual reliability framework, which evaluates model robustness to biased statements by considering the various contexts in which they may appear. We develop the Context-Oriented Bias Indicator and Assessment Score (COBIAS) to measure a biased statement’s reliability in detecting bias, based on the variance in model behavior across different contexts. To evaluate the metric, we augmented 2,291 stereotyped statements from two existing benchmark datasets by adding contextual information. We show that COBIAS aligns with human judgment on the contextual reliability of biased statements (Spearman’s 𝜌 = 0.65, 𝑝 = 3.4 ∗ 10−60) and can be used to create reliable benchmarks, which would assist bias mitigation works.

Abstract

Chemical reaction prediction, encompassing forward synthesis and retrosynthesis, stands as a fundamental challenge in organic synthesis. A widely adopted computational approach frames synthesis prediction as a sequence-to-sequence translation task, using the commonly used SMILES representation for molecules. The current evaluation of machine learning methods for retrosynthesis assumes perfect training data, overlooking imperfections in reaction equations in popular datasets, such as missing reactants, products, other physical and practical constraints such as temperature and cost, primarily due to a focus on the target molecule. This limitation leads to an incomplete representation of viable synthetic routes, especially when multiple sets of reactants can yield a given desired product. In response to these shortcomings, this study examines the prevailing evaluation methods and introduces comprehensive metrics designed to address imperfections in the dataset. Our novel metrics not only assess absolute accuracy by comparing predicted outputs with ground truth but also introduce a nuanced evaluation approach. We provide scores for partial correctness and compute adjusted accuracy through graph matching, acknowledging the inherent complexities of retrosynthetic pathways. Additionally, we explore the impact of small molecular augmentations while preserving chemical properties and employ similarity matching to enhance the assessment of prediction quality. We introduce SynFormer, a sequence-to-sequence model tailored for SMILES representation. It incorporates architectural enhancements to the original transformer, effectively tackling the challenges of chemical reaction prediction. SynFormer achieves a Top-1 accuracy of 53.2% on the USPTO-50k dataset, matching the performance of widely accepted models like Chemformer, but with greater efficiency by eliminating the need for pre-training.

Abstract

Design codes and standards provide a range of values for structural behavior factor for precast reinforced concrete (RC) structural systems. However, most of the codes give common value for all kinds of precast RC structural systems, due to the lack of information from experimental studies. Thus, the present paper highlights experimental investigation on behavior of different precast RC structural systems through quasi-static reversed cyclic tests on precast RC systems subjected to displacement-controlled loading. Different precast RC structural systems tested are precast RC wall-column system, precast RC double leaf system and precast RC beam-column joints with different configurations. Damage assessment has been carried out through observations and data obtained from the experiments, which has been co-related with the grade of damage, damage index and deformation capacity. Consequently, structural behavior factor for different precast RC structural systems has been determined. The structural behavior factor thus obtained would be beneficial for practising engineers and structural designers for analysis and design of different precast RC structural systems.

Abstract

Summarizing movie screenplays presents a unique set of challenges compared to standard document summarization. Screenplays are not only lengthy, but also feature a complex interplay of characters, dialogues, and scenes, with numerous direct and subtle relationships and contextual nuances that are difficult for machine learning models to accurately capture and comprehend. Recent attempts at screenplay summarization focus on fine-tuning transformer-based pre-trained models, but these models often fall short in capturing long-term dependencies and latent relationships, and frequently encounter the "lost in the middle" issue. To address these challenges, we introduce DiscoGraMS, a novel resource that represents movie scripts as a movie character-aware discourse graph (CaD Graph). This approach is well-suited for various downstream tasks, such as summarization, question-answering, and salience detection. The model aims to preserve all salient information, offering a more comprehensive and faithful representation of the screenplay's content. We further explore a baseline method that combines the CaD Graph with the corresponding movie script through a late fusion of graph and text modalities, and we present very initial promising results. We have made our code and dataset publicly available.

Abstract

Pronunciation correction is crucial for Text-to- Speech (TTS) systems in production. Traditional methods, which rely on phoneme sequence manipulation, are often cumber- some and error-prone. To address this, we propose Prompt-to- Correct, an editing-based methodology for pronunciation cor- rection in TTS systems using voice prompts. Our approach enables accurate, granular corrections at test-time without the need for additional training or fine-tuning. Unlike existing speech editing methods, we eliminate the need for external alignment to determine edit boundaries. By simply providing a correctly-pronounced reading of a word in any voice or accent, our system successfully corrects mispronunciations while maintaining continuity. Experimental results demonstrate that our method outperforms traditional baselines and state-of-the- art speech editing techniques. Speech samples are available at: https://prompt-to-correct.github.io/P2C

Abstract

Recently, the exponential growth in capability and pervasiveness of Large Language Models (LLMs) has led to significant work done in the field of code generation. However, this generation has been limited to code snippets. Going one step further, our desideratum is to automatically generate architectural components. This would not only speed up development time, but would also enable us to eventually completely skip the development phase, moving directly from design decisions to deployment. To this end, we conduct an exploratory study on the capability of LLMs to generate architectural components for Functions as a Service (FaaS), commonly known as serverless functions. The small size of their architectural components make this architectural style amenable for generation using current LLMs compared to other styles like monoliths and microservices. We perform the study by systematically selecting open source serverless repositories, masking a serverless function and utilizing state of the art LLMs provided with varying levels of context information about the overall system to generate the masked function. We evaluate correctness through existing tests present in the repositories and use metrics from the Software Engineering (SE) and Natural Language Processing (NLP) domains to evaluate code quality and the degree of similarity between human and LLM generated code respectively. Along with our findings, we also present a discussion on the path forward for using GenAI in architectural component generation.

Abstract

Principal Component Analysis (PCA) is a widely used method for dimensionality reduction, but it often overlooks fairness, especially when working with data that includes demographic characteristics. This can lead to biased representations that disproportionately affect certain groups. To address this issue, our approach incorporates Joint Eigenvalue Decomposition (JEVD), a technique that enables the simultaneous diagonalization of multiple matrices, ensuring both fair and efficient representations. We formally show that the optimal solution of JEVD leads to a fair PCA solution. By integrating JEVD with PCA, we strike an optimal balance between preserving data structure and promoting fairness across diverse groups. We demonstrate that our method outperforms existing baseline approaches in fairness and representational quality on various datasets. It retains the core advantages of PCA while ensuring that sensitive demographic attributes do not create disparities in the reduced representation.

Abstract

Automatic detection of prominence at the word and syllable-levels is critical for building computer-assisted language learning systems. It has been shown that prosody embeddings learned by the current state-of-the-art (SOTA) text-to-speech (TTS) systems could generate word- and syllable-level prominence in the synthesized speech as natural as in native speech. To understand the effectiveness of prosody embeddings from TTS for prominence detection under nonnative context, a comparative analysis is conducted on the embeddings extracted from native and non-native speech considering the prominence-related embeddings: duration, energy, and pitch from a SOTA TTS named FastSpeech2. These embeddings are extracted under two conditions considering: 1) only text, 2) both speech and text. For the first condition, the embeddings are extracted directly from the TTS inference mode, whereas for the second condition, we propose to extract from the TTS under training mode. Experiments are conducted on native speech corpus: Tatoeba, and non-native speech corpus: ISLE. For experimentation, word-level prominence locations are manually annotated for both corpora. The highest relative improvement on word & syllable-level prominence detection accuracies with the TTS embeddings are found to be 13.7% & 5.9% and 16.2% & 6.9% compared to those with the heuristic-based features and self-supervised Wav2Vec-2.0 representations, respectively.

Abstract

Vision-language models (VLMs) excel at tasks requiring joint understanding of visual and linguistic information. A particularly promising yet under-explored application for these models lies in answering questions based on various kinds of maps. This study investigates the efficacy of VLMs in answering questions based on choropleth maps, which are widely used for data analysis and representation. To facilitate and encourage research in this area, we introduce a novel map-based question-answering benchmark, consisting of maps from three geographical regions (United States, India, China), each containing around 1000 questions. Our benchmark incorporates 43 diverse question templates, requiring nuanced understanding of relative spatial relationships, intricate map features, and complex reasoning. It also includes maps with discrete and continuous values, covering variations in color mapping, category ordering, and stylistic patterns, enabling a comprehensive analysis. We evaluated the performance of multiple VLMs on this benchmark, highlighting gaps in their abilities, and providing insights for improving such models. Our dataset, along with all necessary code scripts, is available at map-wise.github.io

Abstract

We present EditIQ, a completely automated framework for cinematically editing scenes captured via a stationary, large field-of-view and high-resolution camera. From the static camera feed, EditIQ initially generates multiple virtual feeds, emulating a team of cameramen. These virtual camera shots termed rushes are subsequently assembled using an automated editing algorithm, whose objective is to present the viewer with the most vivid scene content. To understand key scene elements and guide the editing process, we employ a two-pronged approach: (1) a large language model (LLM)-based dialogue understanding module to analyze conversational flow, coupled with (2) visual saliency prediction to identify meaningful scene elements and camera shots therefrom. We then formulate cinematic video editing as an energy minimization problem over shot selection, where cinematic constraints determine shot choices, transitions, and continuity. EditIQ synthesizes an aesthetically and visually compelling representation of the original narrative while maintaining cinematic coherence and a smooth viewing experience. Efficacy of EditIQ against competing baselines is demonstrated via a psychophysical study involving twenty participants on the BBC Old School dataset plus eleven theatre performance videos. Video samples from EditIQ can be found at https://editiq-ave.github.io/.