Accurately quantifying a large language model's (LLM) predictive uncertainty is crucial for judging the reliability of its answers. While most existing research focuses on short, directly answerable questions with closed-form outputs (e.g., multiple-choice), involving intermediate reasoning steps in LLM responses is increasingly important. This added complexity complicates uncertainty quantification (UQ) because the probabilities assigned to answer tokens are conditioned on a vast space of preceding reasoning tokens. Direct marginalization is infeasible, and the dependency inflates probability estimates, causing overconfidence in UQ. To address this, we propose UQAC, an efficient method that narrows the reasoning space to a tractable size for marginalization. UQAC iteratively constructs an "attention chain" of tokens deemed "semantically crucial" to the final answer via a backtracking procedure. Starting from the answer tokens, it uses attention weights to identify the most influential predecessors, then iterates this process until reaching the input tokens. Similarity filtering and probability thresholding further refine the resulting chain, allowing us to approximate the marginal probabilities of the answer tokens, which serve as the LLM's confidence. We validate UQAC on multiple reasoning benchmarks with advanced open-source LLMs, demonstrating that it consistently delivers reliable UQ estimates with high computational efficiency.

--This study addresses the technical bottlenecks in handling long text and the "hallucination" issue caused by insufficient short text information in remote sensing vision-language foundation models (VLFM). We propose a novel vision-language foundation model, LRSCLIP, and a multimodal dataset, LRS2M. The main contributions are as follows: (1) By integrating multi-source remote sensing data and adopting a large language model labeling strategy, we construct the LRS2M dataset, which contains 2 million image-text pairs, providing both short and long texts for the first time, thus solving the problem of semantic granularity limitations in existing datasets; (2) The design of the LRSCLIP architecture based on Long-CLIP's KPS module, which extends CLIP's text processing capacity and achieves fine-grained cross-modal feature alignment through a dual-text loss weighting mechanism. Experimental results show that LRSCLIP improves retrieval accuracy by 10%-20% over the Long-CLIP baseline in the zero-shot long-text cross-modal retrieval task. For the zero-shot short-text cross-modal retrieval task, LRSCLIP achieves improvements over the current best model, GeoRSCLIP, with increases of 0.17%, 0.67%, and 0.92% in T ext to Image R@1, Image to T ext R@1, and mR on RSITMD, respectively, and 0.04%, 2.93%, and 1.28% on RSICD. This work provides a new benchmark model and data support for remote sensing multimodal learning. ECENT years have seen significant progress in foundation models (FM) within the fields of computer vision (CV) and natural language processing (NLP) [1] [2] [3] [4] [5] [6] [7] [8]. This research was funded by the National Key R&D Program of China under grant number 2021YFB3900504. Weizhi Chen, Kai Li are with Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China, and also with School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China. Jingbo Chen, Y upeng Deng, Jiansheng Chen, Zhihao Xi, Diyou Liu, Y u Meng are with Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China. Y uman Feng is with the School of Information Network Security, People's Public Security University of China, Beijing 100038, China. Unlike models designed for specific task objectives, VLFM learns joint representations of massive image-text pairs in upstream tasks and then transfers this knowledge to various downstream tasks, demonstrating exceptional performance. Several outstanding VLFM models have already emerged, such as CLIP [10], BLIP [11] [12], and MaskVLM [13]. Meanwhile, researchers have begun exploring the application potential of VLFM in the remote sensing domain. However, VLFM often faces issues related to the long-tail effect (where a small number of classes dominate while the rest have fewer samples), making direct application to remote sensing tasks challenging [14].

Large Language Models (LLMs) offer the potential to automate hiring by matching job descriptions with candidate resumes, streamlining recruitment processes, and reducing operational costs. However, biases inherent in these models may lead to unfair hiring practices, reinforcing societal prejudices and undermining workplace diversity. This study examines the performance and fairness of LLMs in job-resume matching tasks within the English language and U.S. context. It evaluates how factors such as gender, race, and educational background influence model decisions, providing critical insights into the fairness and reliability of LLMs in HR applications. Our findings indicate that while recent models have reduced biases related to explicit attributes like gender and race, implicit biases concerning educational background remain significant. These results highlight the need for ongoing evaluation and the development of advanced bias mitigation strategies to ensure equitable hiring practices when using LLMs in industry settings.

The autonomous driving field has seen remarkable advancements in various topics, such as object recognition, trajectory prediction, and motion planning. However, current approaches face limitations in effectively comprehending the complex evolutions of driving scenes over time. This paper proposes FM4SU, a novel methodology for training a symbolic foundation model (FM) for scene understanding in autonomous driving. It leverages knowledge graphs (KGs) to capture sensory observation along with domain knowledge such as road topology, traffic rules, or complex interactions between traffic participants. A bird's eye view (BEV) symbolic representation is extracted from the KG for each driving scene, including the spatio-temporal information among the objects across the scenes. The BEV representation is serialized into a sequence of tokens and given to pre-trained language models (PLMs) for learning an inherent understanding of the co-occurrence among driving scene elements and generating predictions on the next scenes. We conducted a number of experiments using the nuScenes dataset and KG in various scenarios. The results demonstrate that fine-tuned models achieve significantly higher accuracy in all tasks. The fine-tuned T5 model achieved a next scene prediction accuracy of 86.7%. This paper concludes that FM4SU offers a promising foundation for developing more comprehensive models for scene understanding in autonomous driving.

In recent years, large language models (LLMs) have shown an impressive ability to perform arithmetic and symbolic reasoning tasks. However, we found that LLMs (e.g., ChatGPT) cannot perform well on reasoning that requires multiple rounds of dialogue, especially when solving situation puzzles. Specifically, LLMs intend to ask very detailed questions focusing on a specific aspect or same/similar questions after several rounds of Q&As. To help LLMs get out of the above dilemma, we propose a novel external reformulation methodology, where the situation puzzle will be reformulated after several rounds of Q&A or when the LLMs raise an incorrect guess. Experiments show superior performance (e.g., win rate, number of question/guess attempts) of our method than directly using LLMs for solving situation puzzles, highlighting the potential of strategic problem reformulation to enhance the reasoning capabilities of LLMs in complex interactive scenarios.

Network attack detection is a pivotal technology to identify network anomaly and classify malicious traffic. Large Language Models (LLMs) are trained on a vast corpus of text, have amassed remarkable capabilities of context-understanding and commonsense knowledge. This has opened up a new door for network threat detection. Researchers have already initiated discussions regarding the application of LLMs on specific cyber-security tasks. Unfortunately, there is still a lack of comprehensive elaboration how to mine LLMs' potentials in network threat detections, as well as the opportunities and challenges. In this paper, we mainly focus on the classification of malicious traffic from the perspective of LLMs' capability. We present a holistic view of the architecture of LLM-powered network attack detection, including Pre-training, Fine-tuning, and Detection. Especially, by exploring the knowledge and capabilities of LLM, we identify three distinct roles LLM can act in network attack detection: \textit{Classifier, Encoder, and Predictor}. For each of them, the modeling paradigm, opportunities and challenges are elaborated. Finally, we present our design on LLM-powered DDoS detection as a case study. The proposed framework attains accurate detection on carpet bombing DDoS by exploiting LLMs' capabilities in contextual mining. The evaluation shows its efficacy, exhibiting a nearly $35$\% improvement compared to existing systems.

Language models often struggle with temporal misalignment, performance degradation caused by shifts in the temporal distribution of data. Continuously updating models to avoid degradation is expensive. Can models be adapted without updating model weights? We present TARDIS, an unsupervised representation editing method that addresses this challenge. TARDIS extracts steering vectors from unlabeled data and adjusts the model's representations to better align with the target time period's distribution. Our experiments reveal that TARDIS enhances downstream task performance without the need for fine-tuning, can mitigate temporal misalignment even when exact target time period data is unavailable, and remains efficient even when the temporal information of the target data points is unknown at inference time.

As the scale and capabilities of Large Language Models (LLMs) increase, their applications in knowledge-intensive fields such as legal domain have garnered widespread attention. However, it remains doubtful whether these LLMs make judgments based on domain knowledge for reasoning. If LLMs base their judgments solely on specific words or patterns, rather than on the underlying logic of the language, the ''LLM-as-judges'' paradigm poses substantial risks in the real-world applications. To address this question, we propose a method of legal knowledge injection attacks for robustness testing, thereby inferring whether LLMs have learned legal knowledge and reasoning logic. In this paper, we propose J&H: an evaluation framework for detecting the robustness of LLMs under knowledge injection attacks in the legal domain. The aim of the framework is to explore whether LLMs perform deductive reasoning when accomplishing legal tasks. To further this aim, we have attacked each part of the reasoning logic underlying these tasks (major premise, minor premise, and conclusion generation). We have collected mistakes that legal experts might make in judicial decisions in the real world, such as typos, legal synonyms, inaccurate external legal statutes retrieval. However, in real legal practice, legal experts tend to overlook these mistakes and make judgments based on logic. However, when faced with these errors, LLMs are likely to be misled by typographical errors and may not utilize logic in their judgments. We conducted knowledge injection attacks on existing general and domain-specific LLMs. Current LLMs are not robust against the attacks employed in our experiments. In addition we propose and compare several methods to enhance the knowledge robustness of LLMs.

The emergence of large language models and their applications as AI agents have significantly advanced state-of-the-art code generation benchmarks, transforming modern software engineering tasks. However, even with test-time computed reasoning models, these systems still struggle with complex software engineering challenges. This work introduces CURA, a code understanding and reasoning agent system enhanced with verbal process supervision (VPS), achieving a 3.65\% improvement over baseline models on challenging benchmarks like BigCodeBench. Furthermore, CURA, when paired with the o3-mini model and VPS techniques, attains state-of-the-art performance. This work represents a step forward in integrating reasoning-driven architectures with LLM-based code generation, enabling agentic reasoning for language models to solve complex software engineering tasks.

Large Foundation Models (LFMs) have unlocked new possibilities in human-computer interaction, particularly with the rise of mobile Graphical User Interface (GUI) Agents capable of interpreting GUIs. These agents promise to revolutionize mobile computing by allowing users to automate complex mobile tasks through simple natural language instructions. However, the inherent probabilistic nature of LFMs, coupled with the ambiguity and context-dependence of mobile tasks, makes LFM-based automation unreliable and prone to errors. To address this critical challenge, we introduce VeriSafe Agent (VSA): a formal verification system that serves as a logically grounded safeguard for Mobile GUI Agents. VSA is designed to deterministically ensure that an agent's actions strictly align with user intent before conducting an action. At its core, VSA introduces a novel autoformalization technique that translates natural language user instructions into a formally verifiable specification, expressed in our domain-specific language (DSL). This enables runtime, rule-based verification, allowing VSA to detect and prevent erroneous actions executing an action, either by providing corrective feedback or halting unsafe behavior. To the best of our knowledge, VSA is the first attempt to bring the rigor of formal verification to GUI agent. effectively bridging the gap between LFM-driven automation and formal software verification. We implement VSA using off-the-shelf LLM services (GPT-4o) and evaluate its performance on 300 user instructions across 18 widely used mobile apps. The results demonstrate that VSA achieves 94.3%-98.33% accuracy in verifying agent actions, representing a significant 20.4%-25.6% improvement over existing LLM-based verification methods, and consequently increases the GUI agent's task completion rate by 90%-130%.