Search

Standard Neural Machine Translation (NMT) models have traditionally been trained with Sinusoidal Positional Embeddings (PEs), which are inadequate for capturing long-range dependencies and are inefficient for long-context or document-level translation. In contrast, state-of-the-art large language models (LLMs) employ relative PEs, demonstrating superior length generalization. This work explores the potential for efficiently switching the Positional Embeddings of pre-trained NMT models from absolute sinusoidal PEs to relative approaches such as RoPE and ALiBi. Our findings reveal that sinusoidal PEs can be effectively replaced with RoPE and ALiBi with negligible or no performance loss, achieved by fine-tuning on a small fraction of high-quality data. Additionally, models trained without Positional Embeddings (NoPE) are not a viable solution for Encoder-Decoder architectures, as they consistently under-perform compared to models utilizing any form of Positional Embedding. Furthermore, even a model trained from scratch with these relative PEs slightly under-performs a fine-tuned model, underscoring the efficiency and validity of our hypothesis., Comment: Under Review

The rapid decline in groundwater around the world poses a significant challenge to sustainable agriculture. To address this issue, agricultural managed aquifer recharge (Ag-MAR) is proposed to recharge the aquifer by artificially flooding agricultural lands using surface water. Ag-MAR requires a carefully selected flooding schedule to avoid affecting the oxygen absorption of crop roots. However, current Ag-MAR scheduling does not take into account complex environmental factors such as weather and soil oxygen, resulting in crop damage and insufficient recharging amounts. This paper proposes MARLP, the first end-to-end data-driven control system for Ag-MAR. We first formulate Ag-MAR as an optimization problem. To that end, we analyze four-year in-field datasets, which reveal the multi-periodicity feature of the soil oxygen level trends and the opportunity to use external weather forecasts and flooding proposals as exogenous clues for soil oxygen prediction. Then, we design a two-stage forecasting framework. In the first stage, it extracts both the cross-variate dependency and the periodic patterns from historical data to conduct preliminary forecasting. In the second stage, it uses weather-soil and flooding-soil causality to facilitate an accurate prediction of soil oxygen levels. Finally, we conduct model predictive control (MPC) for Ag-MAR flooding. To address the challenge of large action spaces, we devise a heuristic planning module to reduce the number of flooding proposals to enable the search for optimal solutions. Real-world experiments show that MARLP reduces the oxygen deficit ratio by 86.8% while improving the recharging amount in unit time by 35.8%, compared with the previous four years., Comment: Accepted by KDD 2024

Socio-demographic prompting is a commonly employed approach to study cultural biases in LLMs as well as for aligning models to certain cultures. In this paper, we systematically probe four LLMs (Llama 3, Mistral v0.2, GPT-3.5 Turbo and GPT-4) with prompts that are conditioned on culturally sensitive and non-sensitive cues, on datasets that are supposed to be culturally sensitive (EtiCor and CALI) or neutral (MMLU and ETHICS). We observe that all models except GPT-4 show significant variations in their responses on both kinds of datasets for both kinds of prompts, casting doubt on the robustness of the culturally-conditioned prompting as a method for eliciting cultural bias in models or as an alignment strategy. The work also calls rethinking the control experiment design to tease apart the cultural conditioning of responses from "placebo effect", i.e., random perturbations of model responses due to arbitrary tokens in the prompt.

The deployment of Large Language Models (LLMs) in real-world applications presents both opportunities and challenges, particularly in multilingual and code-mixed communication settings. This research evaluates the performance of seven leading LLMs in sentiment analysis on a dataset derived from multilingual and code-mixed WhatsApp chats, including Swahili, English and Sheng. Our evaluation includes both quantitative analysis using metrics like F1 score and qualitative assessment of LLMs' explanations for their predictions. We find that, while Mistral-7b and Mixtral-8x7b achieved high F1 scores, they and other LLMs such as GPT-3.5-Turbo, Llama-2-70b, and Gemma-7b struggled with understanding linguistic and contextual nuances, as well as lack of transparency in their decision-making process as observed from their explanations. In contrast, GPT-4 and GPT-4-Turbo excelled in grasping diverse linguistic inputs and managing various contextual information, demonstrating high consistency with human alignment and transparency in their decision-making process. The LLMs however, encountered difficulties in incorporating cultural nuance especially in non-English settings with GPT-4s doing so inconsistently. The findings emphasize the necessity of continuous improvement of LLMs to effectively tackle the challenges of culturally nuanced, low-resource real-world settings and the need for developing evaluation benchmarks for capturing these issues.

Nucleon weak matrix elements can be extracted from nucleon correlation functions with lattice QCD simulations. The signal-to-noise ratio prohibits the analysis at large source-sink separations and as a consequence, excited state contamination affects the extraction of the nucleon matrix elements. Chiral perturbation theory (ChPT) suggests that the dominant contamination in some of these channels is due to $N\pi$ states where the pion carries the same momentum of the current. In this talk, we report updates on the variational analysis with $qqq$-operators (nucleon-like) and $(qqq)(\bar{q}q)$-operators (nucleon-pion-like) where we report for the first time some preliminary results of $\langle N\pi| \mathcal{J}| N \rangle $, modulo some kinematic and volume factors, and we compare the results against ChPT. This pilot study is performed on a CLS ensemble with $N_f=3$, $m_\pi \approx 420~\mathrm{MeV}$, $a\approx 0.1~\mathrm{fm}$ and $T=2L\approx 4.8~\mathrm{fm}$., Comment: Proceedings for the EuroPLEx Final Conference, 11-15 September 2023, Humboldt University of Berlin

Large language models (LLMs) are at the forefront of transforming numerous domains globally. However, their inclusivity and effectiveness remain limited for non-Latin scripts and low-resource languages. This paper tackles the imperative challenge of enhancing the multilingual performance of LLMs without extensive training or fine-tuning. Through systematic investigation and evaluation of diverse languages using popular question-answering (QA) datasets, we present novel techniques that unlock the true potential of LLMs in a polyglot landscape. Our approach encompasses three key strategies that yield significant improvements in multilingual proficiency. First, by meticulously optimizing prompts tailored for polyglot LLMs, we unlock their latent capabilities, resulting in substantial performance boosts across languages. Second, we introduce a new hybrid approach that synergizes LLM Retrieval Augmented Generation (RAG) with multilingual embeddings and achieves improved multilingual task performance. Finally, we introduce a novel learning approach that dynamically selects the optimal prompt strategy, LLM model, and embedding model per query at run-time. This dynamic adaptation maximizes the efficacy of LLMs across languages, outperforming best static and random strategies. Additionally, our approach adapts configurations in both offline and online settings, and can seamlessly adapt to new languages and datasets, leading to substantial advancements in multilingual understanding and generation across diverse languages.

This paper explores the seamless integration of Generative AI (GenAI) and Evolutionary Algorithms (EAs) within the domain of large-scale multi-objective optimization. Focusing on the transformative role of Large Language Models (LLMs), our study investigates the potential of LLM-Assisted Inference to automate and enhance decision-making processes. Specifically, we highlight its effectiveness in illuminating key decision variables in evolutionarily optimized solutions while articulating contextual trade-offs. Tailored to address the challenges inherent in inferring complex multi-objective optimization solutions at scale, our approach emphasizes the adaptive nature of LLMs, allowing them to provide nuanced explanations and align their language with diverse stakeholder expertise levels and domain preferences. Empirical studies underscore the practical applicability and impact of LLM-Assisted Inference in real-world decision-making scenarios., Comment: Accepted IJCNN

Existing research in measuring and mitigating gender bias predominantly centers on English, overlooking the intricate challenges posed by non-English languages and the Global South. This paper presents the first comprehensive study delving into the nuanced landscape of gender bias in Hindi, the third most spoken language globally. Our study employs diverse mining techniques, computational models, field studies and sheds light on the limitations of current methodologies. Given the challenges faced with mining gender biased statements in Hindi using existing methods, we conducted field studies to bootstrap the collection of such sentences. Through field studies involving rural and low-income community women, we uncover diverse perceptions of gender bias, underscoring the necessity for context-specific approaches. This paper advocates for a community-centric research design, amplifying voices often marginalized in previous studies. Our findings not only contribute to the understanding of gender bias in Hindi but also establish a foundation for further exploration of Indic languages. By exploring the intricacies of this understudied context, we call for thoughtful engagement with gender bias, promoting inclusivity and equity in linguistic and cultural contexts beyond the Global North., Comment: Accepted to FAccT 2024

In recent years, the field of Transfer Evolutionary Optimization (TrEO) has witnessed substantial growth, fueled by the realization of its profound impact on solving complex problems. Numerous algorithms have emerged to address the challenges posed by transferring knowledge between tasks. However, the recently highlighted ``no free lunch theorem'' in transfer optimization clarifies that no single algorithm reigns supreme across diverse problem types. This paper addresses this conundrum by adopting a benchmarking approach to evaluate the performance of various TrEO algorithms in realistic scenarios. Despite the growing methodological focus on transfer optimization, existing benchmark problems often fall short due to inadequate design, predominantly featuring synthetic problems that lack real-world relevance. This paper pioneers a practical TrEO benchmark suite, integrating problems from the literature categorized based on the three essential aspects of Big Source Task-Instances: volume, variety, and velocity. Our primary objective is to provide a comprehensive analysis of existing TrEO algorithms and pave the way for the development of new approaches to tackle practical challenges. By introducing realistic benchmarks that embody the three dimensions of volume, variety, and velocity, we aim to foster a deeper understanding of algorithmic performance in the face of diverse and complex transfer scenarios. This benchmark suite is poised to serve as a valuable resource for researchers, facilitating the refinement and advancement of TrEO algorithms in the pursuit of solving real-world problems., Comment: 17 pages, 18 figures

We investigate resource allocation for quantum entanglement distribution over an optical network. We characterize and model a network architecture that employs a single quasi-deterministic time-frequency heralded Einstein-Podolsky-Rosen (EPR) pair source, and develop a routing scheme for distributing entangled photon pairs over such a network. We focus on max-min fairness in entanglement distribution and compare the performance of various spectrum allocation schemes by examining the max-min and median number of EPR-pairs assigned by them, and the Jain index associated with this assignment. Since this presents an NP-hard problem, we identify two approximation algorithms that outperform others in minimum and mean EPR-pair rate distribution and are comparable to others in the Jain index. We also analyze how the network size and connectivity affect these metrics using Watts-Strogatz random graphs. We find that a spectrum allocation approach that achieves high minimum EPR-pair rate can perform significantly worse when the median EPR-pair rate, Jain index, and runtimes are considered., Comment: arXiv admin note: substantial text overlap with arXiv:2311.14613

With the rising human-like precision of Large Language Models (LLMs) in numerous tasks, their utilization in a variety of real-world applications is becoming more prevalent. Several studies have shown that LLMs excel on many standard NLP benchmarks. However, it is challenging to evaluate LLMs due to test dataset contamination and the limitations of traditional metrics. Since human evaluations are difficult to collect, there is a growing interest in the community to use LLMs themselves as reference-free evaluators for subjective metrics. However, past work has shown that LLM-based evaluators can exhibit bias and have poor alignment with human judgments. In this study, we propose a framework for an end-to-end assessment of LLMs as evaluators in multilingual scenarios. We create a carefully curated dataset, covering 10 languages containing native speaker judgments for the task of summarization. This dataset is created specifically to evaluate LLM-based evaluators, which we refer to as meta-evaluation (METAL). We compare the performance of LLM-based evaluators created using GPT-3.5-Turbo, GPT-4, and PaLM2. Our results indicate that LLM-based evaluators based on GPT-4 perform the best across languages, while GPT-3.5-Turbo performs poorly. Additionally, we perform an analysis of the reasoning provided by LLM-based evaluators and find that it often does not match the reasoning provided by human judges., Comment: Accepted to NAACL 2024 findings

Generative models are increasingly being used in various applications, such as text generation, commonsense reasoning, and question-answering. To be effective globally, these models must be aware of and account for local socio-cultural contexts, making it necessary to have benchmarks to evaluate the models for their cultural familiarity. Since the training data for LLMs is web-based and the Web is limited in its representation of information, it does not capture knowledge present within communities that are not on the Web. Thus, these models exacerbate the inequities, semantic misalignment, and stereotypes from the Web. There has been a growing call for community-centered participatory research methods in NLP. In this work, we respond to this call by using participatory research methods to introduce $\textit{DOSA}$, the first community-generated $\textbf{D}$ataset $\textbf{o}$f 615 $\textbf{S}$ocial $\textbf{A}$rtifacts, by engaging with 260 participants from 19 different Indian geographic subcultures. We use a gamified framework that relies on collective sensemaking to collect the names and descriptions of these artifacts such that the descriptions semantically align with the shared sensibilities of the individuals from those cultures. Next, we benchmark four popular LLMs and find that they show significant variation across regional sub-cultures in their ability to infer the artifacts.

Unrolling training trajectories over time strongly influences the inference accuracy of neural network-augmented physics simulators. We analyze these effects by studying three variants of training neural networks on discrete ground truth trajectories. In addition to commonly used one-step setups and fully differentiable unrolling, we include a third, less widely used variant: unrolling without temporal gradients. Comparing networks trained with these three modalities makes it possible to disentangle the two dominant effects of unrolling, training distribution shift and long-term gradients. We present a detailed study across physical systems, network sizes, network architectures, training setups, and test scenarios. It provides an empirical basis for our main findings: A non-differentiable but unrolled training setup supported by a numerical solver can yield 4.5-fold improvements over a fully differentiable prediction setup that does not utilize this solver. We also quantify a difference in the accuracy of models trained in a fully differentiable setup compared to their non-differentiable counterparts. While differentiable setups perform best, the accuracy of unrolling without temporal gradients comes comparatively close. Furthermore, we empirically show that these behaviors are invariant to changes in the underlying physical system, the network architecture and size, and the numerical scheme. These results motivate integrating non-differentiable numerical simulators into training setups even if full differentiability is unavailable. We also observe that the convergence rate of common neural architectures is low compared to numerical algorithms. This encourages the use of hybrid approaches combining neural and numerical algorithms to utilize the benefits of both., Comment: Project Page: https://ge.in.tum.de/publications/how-temporal-unrolling-supports-neural-physics-simulators/ , Github Page: https://github.com/tum-pbs/unrolling

Nowadays, the usage of Large Language Models (LLMs) has increased, and LLMs have been used to generate texts in different languages and for different tasks. Additionally, due to the participation of remarkable companies such as Google and OpenAI, LLMs are now more accessible, and people can easily use them. However, an important issue is how we can detect AI-generated texts from human-written ones. In this article, we have investigated the problem of AI-generated text detection from two different aspects: semantics and syntax. Finally, we presented an AI model that can distinguish AI-generated texts from human-written ones with high accuracy on both multilingual and monolingual tasks using the M4 dataset. According to our results, using a semantic approach would be more helpful for detection. However, there is a lot of room for improvement in the syntactic approach, and it would be a good approach for future work., Comment: Mohammad Heydari Rad, Farhan Farsi, and Shayan Bali have made equal contributions to this work

We present MunTTS, an end-to-end text-to-speech (TTS) system specifically for Mundari, a low-resource Indian language of the Austo-Asiatic family. Our work addresses the gap in linguistic technology for underrepresented languages by collecting and processing data to build a speech synthesis system. We begin our study by gathering a substantial dataset of Mundari text and speech and train end-to-end speech models. We also delve into the methods used for training our models, ensuring they are efficient and effective despite the data constraints. We evaluate our system with native speakers and objective metrics, demonstrating its potential as a tool for preserving and promoting the Mundari language in the digital age., Comment: Accepted to ComputEL-7

This study explores how discussing metaphors for AI can help build awareness of the frames that shape our understanding of AI systems, particularly large language models (LLMs) like ChatGPT. Given the pressing need to teach "critical AI literacy", discussion of metaphor provides an opportunity for inquiry and dialogue with space for nuance, playfulness, and critique. Using a collaborative autoethnographic methodology, we analyzed metaphors from a range of sources, and reflected on them individually according to seven questions, then met and discussed our interpretations. We then analyzed how our reflections contributed to the three kinds of literacies delineated in Selber's multiliteracies framework: functional, critical, and rhetorical. These allowed us to analyze questions of ethics, equity, and accessibility in relation to AI. We explored each metaphor along the dimension of whether or not it was promoting anthropomorphizing, and to what extent such metaphors imply that AI is sentient. Our findings highlight the role of metaphor reflection in fostering a nuanced understanding of AI, suggesting that our collaborative autoethnographic approach as well as the heuristic model of plotting AI metaphors on dimensions of anthropomorphism and multiliteracies, might be useful for educators and researchers in the pursuit of advancing critical AI literacy., Comment: This is a preprint (accepted version) of an article that has been accepted for publication at the journal Open Praxis: https://openpraxis.org/

We investigate resource allocation for quantum entanglement distribution over an optical network. We characterize and model a network architecture that employs a single quasideterministic time-frequency heralded EPR-pair source, and develop a routing scheme for distributing entangled photon pairs over such a network. We focus on fairness in entanglement distribution, and compare both the performance of various spectrum allocation schemes as well as their Jain index.

There has been a surge in LLM evaluation research to understand LLM capabilities and limitations. However, much of this research has been confined to English, leaving LLM building and evaluation for non-English languages relatively unexplored. Several new LLMs have been introduced recently, necessitating their evaluation on non-English languages. This study aims to perform a thorough evaluation of the non-English capabilities of SoTA LLMs (GPT-3.5-Turbo, GPT-4, PaLM2, Gemini-Pro, Mistral, Llama2, and Gemma) by comparing them on the same set of multilingual datasets. Our benchmark comprises 22 datasets covering 83 languages, including low-resource African languages. We also include two multimodal datasets in the benchmark and compare the performance of LLaVA models, GPT-4-Vision and Gemini-Pro-Vision. Our experiments show that larger models such as GPT-4, Gemini-Pro and PaLM2 outperform smaller models on various tasks, notably on low-resource languages, with GPT-4 outperforming PaLM2 and Gemini-Pro on more datasets. We also perform a study on data contamination and find that several models are likely to be contaminated with multilingual evaluation benchmarks, necessitating approaches to detect and handle contamination while assessing the multilingual performance of LLMs., Comment: 40 pages, 35 figures and 34 tables

Language serves as a powerful tool for the manifestation of societal belief systems. In doing so, it also perpetuates the prevalent biases in our society. Gender bias is one of the most pervasive biases in our society and is seen in online and offline discourses. With LLMs increasingly gaining human-like fluency in text generation, gaining a nuanced understanding of the biases these systems can generate is imperative. Prior work often treats gender bias as a binary classification task. However, acknowledging that bias must be perceived at a relative scale; we investigate the generation and consequent receptivity of manual annotators to bias of varying degrees. Specifically, we create the first dataset of GPT-generated English text with normative ratings of gender bias. Ratings were obtained using Best--Worst Scaling -- an efficient comparative annotation framework. Next, we systematically analyze the variation of themes of gender biases in the observed ranking and show that identity-attack is most closely related to gender bias. Finally, we show the performance of existing automated models trained on related concepts on our dataset., Comment: Camera-ready version in EMNLP 2023

Large Language Models (LLMs) excel in various Natural Language Processing (NLP) tasks, yet their evaluation, particularly in languages beyond the top $20$, remains inadequate due to existing benchmarks and metrics limitations. Employing LLMs as evaluators to rank or score other models' outputs emerges as a viable solution, addressing the constraints tied to human annotators and established benchmarks. In this study, we explore the potential of LLM-based evaluators, specifically GPT-4 in enhancing multilingual evaluation by calibrating them against $20$K human judgments across three text-generation tasks, five metrics, and eight languages. Our analysis reveals a bias in GPT4-based evaluators towards higher scores, underscoring the necessity of calibration with native speaker judgments, especially in low-resource and non-Latin script languages, to ensure accurate evaluation of LLM performance across diverse languages., Comment: Accepted to EACL 2024 findings