Causality detection and mining are important tasks in information retrieval due to their enormous use in information extraction, and knowledge graph construction. To solve these tasks, in existing literature there exist several solutions -- both unsupervised and supervised. However, the unsupervised methods suffer from poor performance and they often require significant human intervention for causal rule selection, leading to poor generalization across different domains. On the other hand, supervised methods suffer from the lack of large training datasets. Recently, large language models (LLMs) with effective prompt engineering are found to be effective to overcome the issue of unavailability of large training dataset. Yet, in existing literature, there does not exist comprehensive works on causality detection and mining using LLM prompting. In this paper, we present several retrieval-augmented generation (RAG) based dynamic prompting schemes to enhance LLM performance in causality detection and extraction tasks. Extensive experiments over three datasets and five LLMs validate the superiority of our proposed RAG-based dynamic prompting over other static prompting schemes.

In this article, we continue the development of the Riemann-Hilbert formalism for studying the asymptotics of Toeplitz+Hankel determinants with non-identical symbols, which we initiated in \cite{GI}. In \cite{GI}, we showed that the Riemann-Hilbert problem we formulated admits the Deift-Zhou nonlinear steepest descent analysis, but with a special restriction on the winding numbers of the associated symbols. In particular, the most natural case, namely zero winding numbers, is not allowed. A principal goal of this paper is to develop a framework that extends the asymptotic analysis of Toeplitz+Hankel determinants to a broader range of winding-number configurations. As an application, we consider the case in which the winding numbers of the Szegő-type Toeplitz and Hankel symbols are zero and one, respectively, and compute the asymptotics of the norms of the corresponding system of orthogonal polynomials.

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models to reflect human preferences, they struggle to capture the distributional pluralistic preferences within a group. These methods often skew toward dominant preferences, overlooking the diversity of opinions, especially when conflicting preferences arise. To address this issue, we propose Group Distributional Preference Optimization (GDPO), a novel framework that aligns language models with the distribution of preferences within a group by incorporating the concept of beliefs that shape individual preferences. GDPO calibrates a language model using statistical estimation of the group's belief distribution and aligns the model with belief-conditioned preferences, offering a more inclusive alignment framework than traditional methods. In experiments using both synthetic controllable opinion generation and real-world movie review datasets, we show that DPO fails to align with the targeted belief distributions, while GDPO consistently reduces this alignment gap during training. Moreover, our evaluation metrics demonstrate that GDPO outperforms existing approaches in aligning with group distributional preferences, marking a significant advance in pluralistic alignment.

Translating culture-related content is vital for effective cross-cultural communication. However, many culture-specific items (CSIs) often lack viable translations across languages, making it challenging to collect high-quality, diverse parallel corpora with CSI annotations. This difficulty hinders the analysis of cultural awareness of machine translation (MT) systems, including traditional neural MT and the emerging MT paradigm using large language models (LLM). To address this gap, we introduce a novel parallel corpus, enriched with CSI annotations in 6 language pairs for investigating Culturally-Aware Machine Translation--CAMT. Furthermore, we design two evaluation metrics to assess CSI translations, focusing on their pragmatic translation quality. Our findings show the superior ability of LLMs over neural MTs in leveraging external cultural knowledge for translating CSIs, especially those lacking translations in the target culture.

Background: Axion-like particles (ALPs) are hypothetical particles that emerge in numerous theoretical extensions to the Standard Model. Their coupling to electromagnetic field implies that ALPs would mix with photons in the presence of external magnetic fields. As ALP phenomenology is governed by the mass and strength of its coupling, there is a subset of this parameter space in which this mixing would be expected to leave an imprint on the spectra of TeV gamma-ray sources. Data: In 2017, the VERITAS gamma-ray observatory recorded the second day of a dramatic flare of the radio galaxy NGC 1275, embedded at the center of the Perseus galaxy cluster. This serendipitous locale provides a spatially-extended magnetic field of strength O(10$\mu$G) through which escaping photons traverse, making it an excellent target to study ALPs. Methods: We analyze the VERITAS data of NGC 1275's 2017 flare with the gammapy analysis package. Extensive fitting and modeling are performed to ultimately conduct a likelihood analysis used to search for any evidence of a preference for ALPs and to explore the confidence with which constraints can be set. We adopt the CLs method for this study for its conservative approach to setting limits in regimes where the search has limited sensitivity. Results: No evidence for the existence of ALPs is found, and no combination of mass and coupling strength can be excluded at or above 95% confidence level. We provide a map showing the strength of our exclusions in the mass and coupling parameter space. The strongest exclusions are found in the mass range $2 \times 10^{-7}$eV $\lesssim m_a \lesssim 4 \times 10^{-7}$eV and at the coupling strength of $g_{a\gamma} \gtrsim 3 \times 10^{-11}$ GeV$^{-1}$ up to 80% confidence level, which are consistent with previous studies. Conclusions: We find the CLs method to be a trustworthy approach, and advocate for its...

The conventional paradigm of using large language models (LLMs) for natural language generation (NLG) evaluation relies on pre-defined task definitions and evaluation criteria, positioning LLMs as "passive critics" that strictly follow developer-provided guidelines. However, human evaluators often apply implicit criteria, and their expectations in practice can vary widely based on specific end-user needs. Consequently, these rigid evaluation methods struggle to adapt to diverse scenarios without extensive prompt customization. To address this, we introduce Active-Critic, a novel LLM-based evaluator that transforms LLMs into "active critics'' capable of adapting to diverse NLG tasks using limited example data. Active-Critic consists of two stages: (1) self-inferring the target NLG task and relevant evaluation criteria, and (2) dynamically optimizing prompts to produce human-aligned scores along with detailed justifications. Our experiments show that Active-Critic can generate nuanced, context-aware evaluation criteria, enabling it to achieve superior alignment with human judgments across multiple tasks.

Extracting cause and effect phrases from a sentence is an important NLP task, with numerous applications in various domains, including legal, medical, education, and scientific research. There are many unsupervised and supervised methods proposed for solving this task. Among these, unsupervised methods utilize various linguistic tools, including syntactic patterns, dependency tree, dependency relations, etc. among different sentential units for extracting the cause and effect phrases. On the other hand, the contemporary supervised methods use various deep learning based mask language models equipped with a token classification layer for extracting cause and effect phrases. Linguistic tools, specifically, dependency tree, which organizes a sentence into different semantic units have been shown to be very effective for extracting semantic pairs from a sentence, but existing supervised methods do not have any provision for utilizing such tools within their model framework. In this work, we propose DepBERT, which extends a transformer-based model by incorporating dependency tree of a sentence within the model framework. Extensive experiments over three datasets show that DepBERT is better than various state-of-the art supervised causality extraction methods.

Recent advances in Generative AI have transformed how users interact with data analysis through natural language interfaces. However, many systems rely too heavily on LLMs, creating risks of hallucination, opaque reasoning, and reduced user control. We present a hybrid visual analysis system that integrates GenAI in a constrained, high-level role to support statistical modeling while preserving transparency and user agency. GenAI translates natural language intent into formal statistical formulations, while interactive visualizations surface model behavior, residual patterns, and hypothesis comparisons to guide iterative exploration. Model fitting, diagnostics, and hypothesis testing are delegated entirely to a structured R-based backend, ensuring correctness, interpretability, and reproducibility. By combining GenAI-assisted intent translation with visualization-driven reasoning, our approach broadens access to modeling tools without compromising rigor. We present an example use case of the tool and discuss challenges and opportunities for future research.

The advancement of Large Language Models (LLMs) has greatly improved our ability to process complex language. However, accurately detecting logical fallacies remains a significant challenge. This study presents a novel and effective prompt formulation approach for logical fallacy detection, applicable in both supervised (fine-tuned) and unsupervised (zero-shot) settings. Our method enriches input text incorporating implicit contextual information -- counterarguments, explanations, and goals -- which we query for validity within the context of the argument. We then rank these queries based on confidence scores to inform classification. We evaluate our approach across multiple datasets from 5 domains, covering 29 distinct fallacy types, using models from the GPT and LLaMA series. The results show substantial improvements over state-of-the-art models, with F1 score increases of up to 0.60 in zero-shot settings and up to 0.45 in fine-tuned models. Extensive analyses further illustrate why and how our method excels.

Transparency is commonly utilized in visualizations to overlay color-coded histograms or sets, thereby facilitating the visual comparison of categorical data. However, these charts often suffer from significant overlap between objects, resulting in substantial color interactions. Existing color blending models struggle in these scenarios, frequently leading to ambiguous color mappings and the introduction of false colors. To address these challenges, we propose an automated approach for generating optimal color encodings to enhance the perception of translucent charts. Our method harnesses color nameability to maximize the association between composite colors and their respective class labels. We introduce a color-name aware (CNA) optimization framework that generates maximally coherent color assignments and transparency settings while ensuring perceptual discriminability for all segments in the visualization. We demonstrate the effectiveness of our technique through crowdsourced experiments with composite histograms, showing how our technique can significantly outperform both standard and visualization-specific color blending models. Furthermore, we illustrate how our approach can be generalized to other visualizations, including parallel coordinates and Venn diagrams. We provide an open-source implementation of our technique as a web-based tool.

Hallucinations in large language models (LLMs) have recently become a significant problem. A recent effort in this direction is a shared task at Semeval 2024 Task 6, SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. This paper describes our winning solution ranked 1st and 2nd in the 2 sub-tasks of model agnostic and model aware tracks respectively. We propose a meta-regressor framework of LLMs for model evaluation and integration that achieves the highest scores on the leaderboard. We also experiment with various transformer-based models and black box methods like ChatGPT, Vectara, and others. In addition, we perform an error analysis comparing GPT4 against our best model which shows the limitations of the former.

Is it secure to measure the reliability of local models by similarity in federated learning (FL)? This paper delves into an unexplored security threat concerning applying similarity metrics, such as the L_2 norm, Euclidean distance, and cosine similarity, in protecting FL. We first uncover the deficiencies of similarity metrics that high-dimensional local models, including benign and poisoned models, may be evaluated to have the same similarity while being significantly different in the parameter values. We then leverage this finding to devise a novel untargeted model poisoning attack, Faker, which launches the attack by simultaneously maximizing the evaluated similarity of the poisoned local model and the difference in the parameter values. Experimental results based on seven datasets and eight defenses show that Faker outperforms the state-of-the-art benchmark attacks by 1.1-9.0X in reducing accuracy and 1.2-8.0X in saving time cost, which even holds for the case of a single malicious client with limited knowledge about the FL system. Moreover, Faker can degrade the performance of the global model by attacking only once. We also preliminarily explore extending Faker to other attacks, such as backdoor attacks and Sybil attacks. Lastly, we provide a model evaluation strategy, called the similarity of partial parameters (SPP), to defend against Faker. Given that numerous mechanisms in FL utilize similarity metrics to assess local models, this work suggests that we should be vigilant regarding the potential risks of using these metrics.

Scientific information extraction (SciIE) has primarily relied on entity-relation extraction in narrow domains, limiting its applicability to interdisciplinary research and struggling to capture the necessary context of scientific information, often resulting in fragmented or conflicting statements. In this paper, we introduce SciEvent, a novel multi-domain benchmark of scientific abstracts annotated via a unified event extraction (EE) schema designed to enable structured and context-aware understanding of scientific content. It includes 500 abstracts across five research domains, with manual annotations of event segments, triggers, and fine-grained arguments. We define SciIE as a multi-stage EE pipeline: (1) segmenting abstracts into core scientific activities--Background, Method, Result, and Conclusion; and (2) extracting the corresponding triggers and arguments. Experiments with fine-tuned EE models, large language models (LLMs), and human annotators reveal a performance gap, with current models struggling in domains such as sociology and humanities. SciEvent serves as a challenging benchmark and a step toward generalizable, multi-domain SciIE.

Predicting the emergence of future research collaborations between authors in academic social networks (SNs) is a very effective example that demonstrates the link prediction problem. This problem refers to predicting the potential existence or absence of a link between a pair of nodes (authors) on the co-authorship network. Various similarity and aggregation metrics were proposed in the literature for predicting the potential link between two authors on such networks. However, the relevant research did not investigate the impact of similarity of research interests of two authors or the similarity of their affiliations on the performance of predicting the potential link between them. Additionally, the impact of the aggregation of the research performance indices of two authors on link prediction performance was not highlighted. To this end, in this paper we propose an integrative supervised learning framework for predicting potential collaboration in co-authorship network based on similarity of the research interests and the similarity of the affiliations of each pair of authors in this network. Moreover, our proposed framework integrates the aggregation of research performance indices of each author pair and the similarity between the two authors nodes with the research interest and affiliation similarity as four metrics for predicting the potential link between each two authors. Our experimental results obtained from applying our proposed link prediction approach to the two largest connected graphs of two huge academic co-authorship networks, namely ArnetMiner and DBLP, show the great performance of this approach in predicting potential links between two authors on large-scale academic SNs.

We consider an $N$-soliton solution of the focusing nonlinear Schrödinger equations. We give conditions for the synchronous collision of these $N$ solitons. When the solitons velocities are well separated and the solitons have equal amplitude, we show that the local wave profile at the collision point scales as the $\operatorname{sinc}(x)$ function. We show that this behaviour persists when the amplitudes of the solitons are i.i.d. sub-exponential random variables. Namely the central collision peak exhibits universality: its spatial profile converges to the $\operatorname{sinc}(x)$ function, independently of the distribution. We derive Central Limit Theorems for the fluctuations of the profile in the near-field regime (near the collision point) and in the far-regime.

Explainable artificial intelligence (XAI) approaches have been increasingly applied in drug discovery to learn molecular representations and identify substructures driving property predictions. However, building end-to-end explainable machine learning models for structure-activity relationship (SAR) modeling for compound property prediction faces many challenges, such as limited activity data per target and the sensitivity of properties to subtle molecular changes. To address this, we leveraged activity-cliff molecule pairs, i.e., compounds sharing a common scaffold but differing sharply in potency, targeting three proto-oncogene tyrosine-protein kinase Src proteins (i.e., PDB IDs 1O42, 2H8H, and 4MXO). We implemented graph neural network (GNN) methods to obtain atom-level feature information and predict compound-protein affinity (i.e., half maximal inhibitory concentration, IC50). In addition, we trained GNN models with different structure-aware loss functions to adequately leverage molecular property and structure information. We also utilized group lasso and sparse group lasso to prune and highlight molecular subgraphs and enhance the structure-specific model explainability for the predicted property difference in molecular activity-cliff pairs. We improved drug property prediction by integrating common and uncommon node information and using sparse group lasso, reducing the average root mean squared error (RMSE) by 12.70%, and achieving the lowest averaged RMSE=0.2551 and the highest PCC=0.9572. Furthermore, applying regularization enhances feature attribution methods that estimate the contribution of each atom in the molecular graphs by boosting global direction scores and atom-level accuracy in atom coloring accuracy, which improves model interpretability in drug discovery pipelines, particularly in investigating important molecular substructures in lead optimization.