Abstract--Negative bias refers to the tendency of large language models (LLMs) to excessively generate negative responses in binary decision tasks (e.g., yes-no question answering). Previous research has focused on detecting and addressing negative attention heads that induce negative bias. However, the underlying detailed factors influencing negative bias remain underexplored. In this paper, we demonstrate that LLMs exhibit format-level negative bias, meaning the prompt format more influences their responses than the semantics of the negative response. For the fine-grained study of the negative bias, we introduce a pipeline for constructing the evaluation set, which systematically categorizes the dataset into three subsets based on the model's parametric knowledge: correct, incorrect, and insufficient relevant knowledge. Through analysis of this evaluation set, we identify a shortcut behavior in which models tend to generate negative responses when they lack sufficient knowledge to answer a yes-no question, leading to negative bias. We further examine how negative bias changes under various prompting scenarios related to parametric knowledge. We observe that providing relevant context and offering an "I don't know" option generally reduces negative bias, whereas chain-of-thought prompting tends to amplify the bias. Finally, we demonstrate that the degree of negative bias can vary depending on the type of prompt, which influences the direction of the response. Our work reveals the various factors that influence negative bias, providing critical insights for mitigating it in LLMs. ECENT advances in the capabilities and emergent abilities of large language models (LLMs) have led to rapid improvements in the performance of a wide range of natural language processing (NLP) tasks [1]-[5]. Leveraging their ability to follow instructions, LLMs are able to perform complex, previously unseen tasks, enabling human-like interactions [6]-[9]. One critical issue is the hallucination problem, where the model generates content that contains misleading information, which does not correspond to the given context or real-world knowledge [11]. J. Song was with the Department of Electrical and Computer Engineering at Seoul National University, South Korea (coms1580@gmail.com).

Large Language Models (LLMs) have become ubiquitous in everyday life and are entering higher-stakes applications ranging from summarizing meeting transcripts to answering doctors' questions. As was the case with earlier predictive models, it is crucial that we develop tools for explaining the output of LLMs, be it a summary, list, response to a question, etc. With these needs in mind, we introduce In-Context Explainability 360 (ICX360), an open-source Python toolkit for explaining LLMs with a focus on the user-provided context (or prompts in general) that are fed to the LLMs. ICX360 contains implementations for three recent tools that explain LLMs using both black-box and white-box methods (via perturbations and gradients respectively).

Context: Ensuring high levels of dependability in modern computer-based systems has become increasingly challenging due to their complexity. Although systems are validated at design time, their behavior can be different at run-time, possibly showing control-flow anomalies due to "unknown unknowns". Objective: We aim to detect control-flow anomalies through software monitoring, which verifies run-time behavior by logging software execution and detecting deviations from expected control flow. Methods: We propose a methodology to develop software monitors for control-flow anomaly detection through Large Language Models (LLMs) and conformance checking. The methodology builds on existing software development practices to maintain traditional V&V while providing an additional level of robustness and trustworthiness. It leverages LLMs to link design-time models and implementation code, automating source-code instrumentation. The resulting event logs are analyzed via conformance checking, an explainable and effective technique for control-flow anomaly detection. Results: We test the methodology on a case-study scenario from the European Railway Traffic Management System / European Train Control System (ERTMS/ETCS), which is a railway standard for modern interoperable railways. The results obtained from the ERTMS/ETCS case study demonstrate that LLM-based source-code instrumentation can achieve up to 84.775% control-flow coverage of the reference design-time process model, while the subsequent conformance checking-based anomaly detection reaches a peak performance of 96.610% F1-score and 93.515% AUC. Conclusion: Incorporating domain-specific knowledge to guide LLMs in source-code instrumentation significantly allowed obtaining reliable and quality software logs and enabled effective control-flow anomaly detection through conformance checking.

Training data imbalance poses a major challenge for code LLMs. Most available data heavily over represents raw opensource code while underrepresenting broader software engineering tasks, especially in low resource languages like Golang. As a result, models excel at code autocompletion but struggle with real world developer workflows such as unit test generation. To address this gap, we introduce GO UT Bench, a benchmark dataset of 5264 pairs of code and unit tests, drawn from 10 permissively licensed Golang repositories spanning diverse domain. We evaluate its effectiveness as a fine tuning dataset across two LLM families i.e. mixture of experts and dense decoders. Our results show that finetuned models outperform their base counterparts on more than 75% of benchmark tasks.

Abstract--This paper proposes a Short-Window Sliding Learning framework for real-time violence detection in CCTV footages. Unlike conventional long-video training approaches, the proposed method divides videos into 1-2 second clips and applies Large Language Model (LLM)-based auto-caption labeling to construct fine-grained datasets. Each short clip fully utilizes all frames to preserve temporal continuity, enabling precise recognition of rapid violent events. Experiments demonstrate that the proposed method achieves 95.25% accuracy on RWF-2000 and significantly improves performance on long videos (UCF-Crime: 83.25%), confirming its strong generalization and real-time applicability in intelligent surveillance systems. Recently, video-based violence and abnormal behavior detection has been gaining attention as an essential core technology in fields such as public safety, smart cities, and intelligent surveillance [1].

Task arithmetic is a powerful technique for transferring skills between Large Language Models (LLMs), but it often suffers from negative interference when models have diverged during training. We address this limitation by first aligning the models' parameter spaces, leveraging the inherent permutation, rotation, and scaling symmetries of Transformer architectures. We adapt parameter space alignment for modern Grouped-Query Attention (GQA) and SwiGLU layers, exploring both weight-based and activation-based approaches. Using this alignment-first strategy, we successfully transfer advanced reasoning skills to a non-reasoning model. Experiments on challenging reasoning benchmarks show that our method consistently outperforms standard task arithmetic. This work provides an effective approach for merging and transferring specialized skills across evolving LLM families, reducing redundant fine-tuning and enhancing model adaptability.

Large Language Models (LLMs) are increasingly deployed in safety-critical domains, yet remain susceptible to hallucinations. While prior works have proposed confidence representation methods for hallucination detection, most of these approaches rely on computationally expensive sampling strategies and often disregard the distinction between hallucination types. In this work, we introduce a principled evaluation framework that differentiates between extrinsic and intrinsic hallucination categories and evaluates detection performance across a suite of curated benchmarks. In addition, we leverage a recent attention-based uncertainty quantification algorithm and propose novel attention aggregation strategies that improve both interpretability and hallucination detection performance. Our experimental findings reveal that sampling-based methods like Semantic Entropy are effective for detecting extrinsic hallucinations but generally fail on intrinsic ones. In contrast, our method, which aggregates attention over input tokens, is better suited for intrinsic hallucinations. These insights provide new directions for aligning detection strategies with the nature of hallucination and highlight attention as a rich signal for quantifying model uncertainty.

Equation discovery from data is a core challenge in machine learning for science, requiring the recovery of concise symbolic expressions that govern complex physical and geometric phenomena. Recent approaches with large language models (LLMs) show promise in symbolic regression, but their success often hinges on memorized formulas or overly simplified functional forms. Existing benchmarks exacerbate this limitation: they focus on scalar functions, ignore domain grounding, and rely on brittle string-matching based metrics that fail to capture scientific equivalence. We introduce SurfaceBench, first comprehensive benchmark for symbolic surface discovery. SurfaceBench comprises 183 tasks across 15 categories of symbolic complexity, spanning explicit, implicit, and parametric equation representation forms. Each task includes ground-truth equations, variable semantics, and synthetically sampled three dimensional data. Unlike prior SR datasets, our tasks reflect surface-level structure, resist LLM memorization through novel symbolic compositions, and are grounded in scientific domains such as fluid dynamics, robotics, electromagnetics, and geometry. To evaluate equation discovery quality, we pair symbolic checks with geometry-aware metrics such as Chamfer and Hausdorff distances, capturing both algebraic fidelity and spatial reconstruction accuracy. Our experiments reveal that state-of-the-art frameworks, while occasionally successful on specific families, struggle to generalize across representation types and surface complexities. SurfaceBench thus establishes a challenging and diagnostic testbed that bridges symbolic reasoning with geometric reconstruction, enabling principled benchmarking of progress in compositional generalization, data-driven scientific induction, and geometry-aware reasoning with LLMs. We release the code here: https://github.com/Sanchit-404/surfacebench

We investigate transformer prediction of long Collatz steps, a complex arithmetic function that maps odd integers to their distant successors in the Collatz sequence ( $u_{n+1}=u_n/2$ if $u_n$ is even, $u_{n+1}=(3u_n+1)/2$ if $u_n$ is odd). Model accuracy varies with the base used to encode input and output. It can be as high as $99.7\%$ for bases $24$ and $32$, and as low as $37$ and $25\%$ for bases $11$ and $3$. Yet, all models, no matter the base, follow a common learning pattern. As training proceeds, they learn a sequence of classes of inputs that share the same residual modulo $2^p$. Models achieve near-perfect accuracy on these classes, and less than $1\%$ for all other inputs. This maps to a mathematical property of Collatz sequences: the length of the loops involved in the computation of a long Collatz step can be deduced from the binary representation of its input. The learning pattern reflects the model learning to predict inputs associated with increasing loop lengths. An analysis of failure cases reveals that almost all model errors follow predictable patterns. Hallucination, a common feature of large language models, almost never happens. In over $90\%$ of failures, the model performs the correct calculation, but wrongly estimates loop lengths. Our observations give a full account of the algorithms learned by the models. They suggest that the difficulty of learning such complex arithmetic function lies in figuring the control structure of the computation -- the length of the loops. We believe that the approach outlined here, using mathematical problems as tools for understanding, explaining, and perhaps improving language models, can be applied to a broad range of problems and bear fruitful results.

Operational safety at mission-critical work sites is a top priority given the complex and hazardous nature of daily tasks. This paper presents the Human-Agent Risk Navigation and Event Safety System (HARNESS), a modular AI framework designed to forecast hazardous events and analyze operational risks in U.S. Department of Energy (DOE) environments. HARNESS integrates Large Language Models (LLMs) with structured work data, historical event retrieval, and risk analysis to proactively identify potential hazards. A human-in-the-loop mechanism allows subject matter experts (SMEs) to refine predictions, creating an adaptive learning loop that enhances performance over time. By combining SME collaboration with iterative agentic reasoning, HARNESS improves the reliability and efficiency of predictive safety systems. Preliminary deployment shows promising results, with future work focusing on quantitative evaluation of accuracy, SME agreement, and decision latency reduction.