Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing additional context or adversarial tokens, leaving the core harmful intent unchanged. In this paper, we introduce ISA (Intent Shift Attack), which obfuscates LLMs about the intent of the attacks. More specifically, we establish a taxonomy of intent transformations and leverage them to generate attacks that may be misperceived by LLMs as benign requests for information. Unlike prior methods relying on complex tokens or lengthy context, our approach only needs minimal edits to the original request, and yields natural, human-readable, and seemingly harmless prompts. Extensive experiments on both open-source and commercial LLMs show that ISA achieves over 70% improvement in attack success rate compared to direct harmful prompts. More critically, fine-tuning models on only benign data reformulated with ISA templates elevates success rates to nearly 100%. For defense, we evaluate existing methods and demonstrate their inadequacy against ISA, while exploring both training-free and training-based mitigation strategies. Our findings reveal fundamental challenges in intent inference for LLMs safety and underscore the need for more effective defenses. Our code and datasets are available at https://github.com/NJUNLP/ISA.

-- Accurate multi - horizon retail forecasts are critical for inventory and promotions. We present a novel study of weekly Walmart sales (45 stores, 2010 - 2012) using a Temporal Fusion Transformer (TFT) that fuses static store identifiers with time - varying exoge nous signals (holidays, CPI, fuel price, temperature). The pipeline produces 1 - 5 - week - ahead probabilistic forecasts via QuantileLoss, yielding calibrated 90% prediction intervals and interpretability through variable - selection networks, static enr ichment, and temporal attention. On a fixed 2012 hold - out dataset, TFT achieves an RMSE of $ 57.9k USD per store - week and an R of 0.9875. Across 5 - fold chronological cross - validation, the averages are RMSE = $ 64.6k USD and R = 0.9844, outperforming XGB, CNN, LSTM, and CNN - LSTM baseline models .

Air pollution, especially the particulate matter 2.5 (PM2.5), has become a growing concern in recent years, primarily in urban areas. Being exposed to air pollution is linked to developing numerous health problems, like the aggravation of respiratory diseases, cardiovascular disorders, lung function impairment, and even cancer or early death. Forecasting future levels of PM2.5 has become increasingly important over the past few years, as it can provide early warnings and help prevent diseases. This paper aims to design, fine-tune, test, and evaluate machine learning models for predicting future levels of PM2.5 over various time horizons. Our primary objective is to assess and compare the performance of multiple models, ranging from linear regression algorithms and ensemble-based methods to deep learning models, such as advanced recurrent neural networks and transformers, as well as large language models, on this forecasting task.

Gender bias in language models has gained increasing attention in the field of natural language processing. Encoder-based transformer models, which have achieved state-of-the-art performance in various language tasks, have been shown to exhibit strong gender biases inherited from their training data. This paper investigates gender bias in contextualized word embeddings, a crucial component of transformer-based models. We focus on prominent architectures such as BERT, ALBERT, RoBERTa, and DistilBERT to examine their vulnerability to gender bias. To quantify the degree of bias, we introduce a novel metric, MALoR, which assesses bias based on model probabilities for filling masked tokens. We further propose a mitigation approach involving continued pre-training on a gender-balanced dataset generated via Counterfactual Data Augmentation. Our experiments reveal significant reductions in gender bias scores across different pronoun pairs. For instance, in BERT-base, bias scores for "he-she" dropped from 1.27 to 0.08, and "his-her" from 2.51 to 0.36 following our mitigation approach. We also observed similar improvements across other models, with "male-female" bias decreasing from 1.82 to 0.10 in BERT-large. Our approach effectively reduces gender bias without compromising model performance on downstream tasks.

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated by the need to accommodate different value systems and precisely align with given safety preferences. Moreover, traditional methods like SFT and RLHF lack this capability due to their costly parameter tuning requirements and inability to support multiple value systems within a single model. These problems are more obvious in multimodal large language models (MLLMs), especially in terms of heightened over-refusal in cross-modal tasks and new security risks arising from expanded attack surfaces. We propose Magic Image, an optimization-driven visual prompt framework that enhances security while reducing over-refusal. By optimizing image prompts using harmful/benign samples, our method enables a single model to adapt to different value systems and better align with given safety preferences without parameter updates. Experiments demonstrate improved safety-effectiveness balance across diverse datasets while preserving model performance, offering a practical solution for deployable MLLM safety alignment.

Large Language Models (LLMs), constrained by limited context windows, often face significant performance degradation when reasoning over long contexts. To address this, Retrieval-Augmented Generation (RAG) retrieves and reasons over chunks but frequently sacrifices logical coherence due to its reliance on similarity-based rankings. Similarly, divide-and-conquer frameworks (DCF) split documents into small chunks for independent reasoning and aggregation. While effective for local reasoning, DCF struggles to capture long-range dependencies and risks inducing conflicts by processing chunks in isolation. To overcome these limitations, we propose ToM, a novel Tree-oriented MapReduce framework for long-context reasoning. ToM leverages the inherent hierarchical structure of long documents (e.g., main headings and subheadings) by constructing a DocTree through hierarchical semantic parsing and performing bottom-up aggregation. Using a Tree MapReduce approach, ToM enables recursive reasoning: in the Map step, rationales are generated at child nodes; in the Reduce step, these rationales are aggregated across sibling nodes to resolve conflicts or reach consensus at parent nodes. Experimental results on 70B+ LLMs show that ToM significantly outperforms existing divide-and-conquer frameworks and retrieval-augmented generation methods, achieving better logical coherence and long-context reasoning. Our code is available at https://github.com/gjn12-31/ToM .

Large Language Models (LLMs) have achieved remarkable progress in code-related tasks. Despite their advancement, empirical evidence reveals that they still struggle with \emph{deductive code reasoning}, the ability to reason about the program execution process. While prior studies have recognized this limitation, the underlying causes remain largely underexplored. In this paper, we begin by presenting a comprehensive empirical study that reveals three key challenges undermining deductive code reasoning: (1) an intrinsic gap between generation and reasoning abilities, (2) a consistent bias towards code sources, and (3) weak zero-shot generalization on complex benchmarks. In light of these challenges, we propose \texttt{ReMind}, a multi-agent framework composed of \texttt{Mutator}, \texttt{Executor}, and \texttt{Inspector}. The \texttt{Mutator} generates code variants to mitigate bias towards code sources, the \texttt{Executor} traces variable states step-by-step to expose inconsistency, and the \texttt{Inspector} identifies problematic reasoning steps and provides control-flow refinement to bridge the intrinsic reasoning gap. Through their coordinated collaboration, \texttt{ReMind} systematically identifies and refines reasoning flaws, achieving outstanding performance and enabling robust zero-shot generalization. Extensive experiments on two benchmarks with five LLMs demonstrate the superior advantages of \texttt{ReMind} compared to baseline approaches in deductive code reasoning.

The linguistic diversity of India poses significant machine translation challenges, especially for underrepresented tribal languages like Bhili, which lack high-quality linguistic resources. This paper addresses the gap by introducing Bhili-Hindi-English Parallel Corpus (BHEPC), the first and largest parallel corpus worldwide comprising 110,000 meticulously curated sentences across Bhili, Hindi, and English. The corpus was created with the assistance of expert human translators. BHEPC spans critical domains such as education, administration, and news, establishing a valuable benchmark for research in low resource machine translation. To establish a comprehensive Bhili Machine Translation benchmark, we evaluated a wide range of proprietary and open-source Multilingual Large Language Models (MLLMs) on bidirectional translation tasks between English/Hindi and Bhili. Comprehensive evaluation demonstrates that the fine-tuned NLLB-200 distilled 600M variant model outperforms others, highlighting the potential of multilingual models in low resource scenarios. Furthermore, we investigated the generative translation capabilities of multilingual LLMs on BHEPC using in-context learning, assessing performance under cross-domain generalization and quantifying distributional divergence. This work bridges a critical resource gap and promotes inclusive natural language processing technologies for low-resource and marginalized languages globally.

Ongoing breakthroughs in Large Language Models (LLMs) are reshaping search and recommendation platforms at their core. While this shift unlocks powerful new scientometric tools, it also exposes critical fairness and bias issues that could erode the integrity of the information ecosystem. Additionally, as LLMs become more integrated into web-based searches for scholarly tools, their ability to generate summarized research work based on memorized data introduces new dimensions to these challenges. The extent of memorization in LLMs can impact the accuracy and fairness of the co-authorship networks they produce, potentially reflecting and amplifying existing biases within the scientific community and across different regions. This study critically examines the impact of LLM memorization on the co-authorship networks. To this end, we assess memorization effects across three prominent models, DeepSeek R1, Llama 4 Scout, and Mixtral 8x7B, analyzing how memorization-driven outputs vary across academic disciplines and world regions. While our global analysis reveals a consistent bias favoring highly cited researchers, this pattern is not uniformly observed. Certain disciplines, such as Clinical Medicine, and regions, including parts of Africa, show more balanced representation, pointing to areas where LLM training data may reflect greater equity. These findings underscore both the risks and opportunities in deploying LLMs for scholarly discovery.

Accurate segmentation of vestibular schwannoma (VS) on Magnetic Resonance Imaging (MRI) is essential for patient management but often requires time-intensive manual annotations by experts. While recent advances in deep learning (DL) have facilitated automated segmentation, challenges remain in achieving robust performance across diverse datasets and complex clinical cases. We present an annotated dataset stemming from a bootstrapped DL-based framework for iterative segmentation and quality refinement of VS in MRI. We combine data from multiple centres and rely on expert consensus for trustworthiness of the annotations. We show that our approach enables effective and resource-efficient generalisation of automated segmentation models to a target data distribution. The framework achieved a significant improvement in segmentation accuracy with a Dice Similarity Coefficient (DSC) increase from 0.9125 to 0.9670 on our target internal validation dataset, while maintaining stable performance on representative external datasets. Expert evaluation on 143 scans further highlighted areas for model refinement, revealing nuanced cases where segmentation required expert intervention. The proposed approach is estimated to enhance efficiency by approximately 37.4% compared to the conventional manual annotation process. Overall, our human-in-the-loop model training approach achieved high segmentation accuracy, highlighting its potential as a clinically adaptable and generalisable strategy for automated VS segmentation in diverse clinical settings. The dataset includes 190 patients, with tumour annotations available for 534 longitudinal contrast-enhanced T1-weighted (T1CE) scans from 184 patients, and non-annotated T2-weighted scans from 6 patients. This dataset is publicly accessible on The Cancer Imaging Archive (TCIA) (https://doi.org/10.7937/bq0z-xa62).