Algorithmic tools are increasingly used in hiring to improve fairness and diversity, often by enforcing constraints such as gender-balanced candidate shortlists. However, we show theoretically and empirically that enforcing equal representation at the shortlist stage does not necessarily translate into more diverse final hires, even when there is no gender bias in the hiring stage. We identify a crucial factor influencing this outcome: the correlation between the algorithm's screening criteria and the human hiring manager's evaluation criteria -- higher correlation leads to lower diversity in final hires. Using a large-scale empirical analysis of nearly 800,000 job applications across multiple technology firms, we find that enforcing equal shortlists yields limited improvements in hire diversity when the algorithmic screening closely mirrors the hiring manager's preferences. We propose a complementary algorithmic approach designed explicitly to diversify shortlists by selecting candidates likely to be overlooked by managers, yet still competitive according to their evaluation criteria. Empirical simulations show that this approach significantly enhances gender diversity in final hires without substantially compromising hire quality. These findings highlight the importance of algorithmic design choices in achieving organizational diversity goals and provide actionable guidance for practitioners implementing fairness-oriented hiring algorithms.

Machine translation (MT) has become indispensable for cross-border communication in globalized industries like e-commerce, finance, and legal services, with recent advancements in large language models (LLMs) significantly enhancing translation quality. However, applying general-purpose MT models to industrial scenarios reveals critical limitations due to domain-specific terminology, cultural nuances, and stylistic conventions absent in generic benchmarks. Existing evaluation frameworks inadequately assess performance in specialized contexts, creating a gap between academic benchmarks and real-world efficacy. To address this, we propose a three-level translation capability framework: (1) Basic Linguistic Competence, (2) Domain-Specific Proficiency, and (3) Cultural Adaptation, emphasizing the need for holistic evaluation across these dimensions. We introduce TransBench, a benchmark tailored for industrial MT, initially targeting international e-commerce with 17,000 professionally translated sentences spanning 4 main scenarios and 33 language pairs. TransBench integrates traditional metrics (BLEU, TER) with Marco-MOS, a domain-specific evaluation model, and provides guidelines for reproducible benchmark construction. Our contributions include: (1) a structured framework for industrial MT evaluation, (2) the first publicly available benchmark for e-commerce translation, (3) novel metrics probing multi-level translation quality, and (4) open-sourced evaluation tools. This work bridges the evaluation gap, enabling researchers and practitioners to systematically assess and enhance MT systems for industry-specific needs.

A question-answering (QA) system is to search suitable answers within a knowledge base. Current QA systems struggle with queries requiring complex reasoning or real-time knowledge integration. They are often supplemented with retrieval techniques on a data source such as Retrieval-Augmented Generation (RAG). However, RAG continues to face challenges in handling complex reasoning and logical connections between multiple sources of information. A novel approach for enhancing Large Language Models (LLMs) in knowledge-intensive QA tasks is presented through the automated generation of context-based QA pairs. This methodology leverages LLMs to create fine-tuning data, reducing reliance on human labelling and improving model comprehension and reasoning capabilities. The proposed system includes an automated QA generator and a model fine-tuner, evaluated using perplexity, ROUGE, BLEU, and BERTScore. Comprehensive experiments demonstrate improvements in logical coherence and factual accuracy, with implications for developing adaptable Artificial Intelligence (AI) systems. Mistral-7b-v0.3 outperforms Llama-3-8b with BERT F1, BLEU, and ROUGE scores 0.858, 0.172, and 0.260 of for the LLM generated QA pairs compared to scores of 0.836, 0.083, and 0.139 for the human annotated QA pairs.

Toxicity detection in multimodal text-image content faces growing challenges, especially with multimodal implicit toxicity, where each modality appears benign on its own but conveys hazard when combined. Multimodal implicit toxicity appears not only as formal statements in social platforms but also prompts that can lead to toxic dialogs from Large Vision-Language Models (LVLMs). Despite the success in unimodal text or image moderation, toxicity detection for multimodal content, particularly the multimodal implicit toxicity, remains underexplored. To fill this gap, we comprehensively build a taxonomy for multimodal implicit toxicity (MMIT) and introduce an MMIT-dataset, comprising 2,100 multimodal statements and prompts across 7 risk categories (31 sub-categories) and 5 typical cross-modal correlation modes. To advance the detection of multimodal implicit toxicity, we build ShieldVLM, a model which identifies implicit toxicity in multimodal statements, prompts and dialogs via deliberative cross-modal reasoning. Experiments show that ShieldVLM outperforms existing strong baselines in detecting both implicit and explicit toxicity. The model and dataset will be publicly available to support future researches. Warning: This paper contains potentially sensitive contents.

Existing research on judicial sentencing prediction predominantly relies on end-to-end models, which often neglect the inherent sentencing logic and lack interpretability-a critical requirement for both scholarly research and judicial practice. To address this challenge, we make three key contributions:First, we propose a novel Saturated Mechanistic Sentencing (SMS) model, which provides inherent legal interpretability by virtue of its foundation in China's Criminal Law. We also introduce the corresponding Momentum Least Mean Squares (MLMS) adaptive algorithm for this model. Second, for the MLMS algorithm based adaptive sentencing predictor, we establish a mathematical theory on the accuracy of adaptive prediction without resorting to any stationarity and independence assumptions on the data. We also provide a best possible upper bound for the prediction accuracy achievable by the best predictor designed in the known parameters case. Third, we construct a Chinese Intentional Bodily Harm (CIBH) dataset. Utilizing this real-world data, extensive experiments demonstrate that our approach achieves a prediction accuracy that is not far from the best possible theoretical upper bound, validating both the model's suitability and the algorithm's accuracy.

This article provides an overview of IG Parser, a software that facilitates qualitative content analysis of formal (e.g., legal) rules or informal (e.g., social) norms, and strategies (such as conventions) -- referred to as institutions -- that govern social systems and operate configurally to describe institutional systems. To this end, the IG Parser employs a distinctive syntax that ensures rigorous encoding of natural language, while automating the transformation into various formats that support the downstream analysis using diverse analytical techniques. The conceptual core of the IG Parser is an associated syntax, IG Script, that operationalizes the conceptual foundations of the Institutional Grammar, and more specifically the Institutional Grammar 2.0, an analytical paradigm for institutional analysis. This article presents the IG Parser, including its conceptual foundations, the syntax specification of IG Script, and its architectural principles. This overview is augmented with selective illustrative examples that highlight its use and the associated benefits.

Can deception be detected solely from written text? Cues of deceptive communication are inherently subtle, even more so in text-only communication. Yet, prior studies have reported considerable success in automatic deception detection. We hypothesize that such findings are largely driven by artifacts introduced during data collection and do not generalize beyond specific datasets. We revisit this assumption by introducing a belief-based deception framework, which defines deception as a misalignment between an author's claims and true beliefs, irrespective of factual accuracy, allowing deception cues to be studied in isolation. Based on this framework, we construct three corpora, collectively referred to as DeFaBel, including a German-language corpus of deceptive and non-deceptive arguments and a multilingual version in German and English, each collected under varying conditions to account for belief change and enable cross-linguistic analysis. Using these corpora, we evaluate commonly reported linguistic cues of deception. Across all three DeFaBel variants, these cues show negligible, statistically insignificant correlations with deception labels, contrary to prior work that treats such cues as reliable indicators. We further benchmark against other English deception datasets following similar data collection protocols. While some show statistically significant correlations, effect sizes remain low and, critically, the set of predictive cues is inconsistent across datasets. We also evaluate deception detection using feature-based models, pretrained language models, and instruction-tuned large language models. While some models perform well on established deception datasets, they consistently perform near chance on DeFaBel. Our findings challenge the assumption that deception can be reliably inferred from linguistic cues and call for rethinking how deception is studied and modeled in NLP.

Identifying subtle technical errors within complex scientific and technical documents, especially those requiring multimodal interpretation (e.g., formulas in images), presents a significant hurdle for Large Language Models (LLMs) whose inherent error-correction tendencies can mask inaccuracies. This exploratory proof-of-concept (PoC) study investigates structured LLM context conditioning, informed by Persistent Workflow Prompting (PWP) principles, as a methodological strategy to modulate this LLM behavior at inference time. The approach is designed to enhance the reliability of readily available, general-purpose LLMs (specifically Gemini 2.5 Pro and ChatGPT Plus o3) for precise validation tasks, crucially relying only on their standard chat interfaces without API access or model modifications. To explore this methodology, we focused on validating chemical formulas within a single, complex test paper with known textual and image-based errors. Several prompting strategies were evaluated: while basic prompts proved unreliable, an approach adapting PWP structures to rigorously condition the LLM's analytical mindset appeared to improve textual error identification with both models. Notably, this method also guided Gemini 2.5 Pro to repeatedly identify a subtle image-based formula error previously overlooked during manual review, a task where ChatGPT Plus o3 failed in our tests. These preliminary findings highlight specific LLM operational modes that impede detail-oriented validation and suggest that PWP-informed context conditioning offers a promising and highly accessible technique for developing more robust LLM-driven analytical workflows, particularly for tasks requiring meticulous error detection in scientific and technical documents. Extensive validation beyond this limited PoC is necessary to ascertain broader applicability.Keywords: AI-assisted, AI-powered, AI-enhanced, automated, knowledge engineering, machine learning.

Within seconds, you've been scanned, stored, and tracked--before even reaching airport security. Without ever handing over your ID, the Transportation Security Administration (TSA) already knows exactly who you are. This is happening at 84 airports across the US. And chances are, you didn't even notice. Marketed as a tool to enhance security, TSA's facial recognition system is drawing criticism for its potential to track Americans from the terminal entrance to their final destination.

Breakthroughs, discoveries, and DIY tips sent every weekday. We like to think our brains are reliable recorders--but reality says otherwise. From misremembered childhood moments to mistakenly "recalling" that you took your pills when you didn't, false memories are surprisingly common. And in high-stakes situations like courtroom testimony, these errors can have devastating consequences. Wouldn't it be amazing if there were an objective way to measure just how accurate someone's memory really is? New research suggests we might be able to do just that--by watching the eyes.