Before You Poll with LLMs: A Deliberative Diagnostic Framework
本文提出了一种框架来评估LLMs在接收新信息后是否能像人类一样更新观点，通过对比模型和人类在相同信息干预后的观点变化，发现现有模型均未能准确模拟人类的观点更新。
0 citationsRead paper
Selected work
Representative Papers
A High-Throughput FPGA Architecture for Real-Time TCP-SYN Scan Detection
该研究提出了一种轻量级FPGA架构，用于实时TCP-SYN扫描检测，通过布尔LUT树并行评估指纹，实现了低延迟和高吞吐量。
0 citationsRead paper
Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation
研究探讨了量化KV缓存对检索增强生成系统忠实性的影响，使用Qwen2.5-7B-Instruct模型在不同量化级别下评估准确性和忠实性。
0 citationsRead paper
Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextualized Urdu Benchmark
研究针对低资源语言中文化不匹配导致的LLM对齐问题，通过创建首个乌尔都语3H基准Pak3H1，并采用人工校验和文化适应方法解决。
0 citationsRead paper
Automated Borehole Core Analysis with Report-Derived Weak Labels and Supervised Crack Segmentation
This study addresses the challenge posed by the absence of pixel-level fracture annotations in core images, which hinders automated extraction of fracture spacing and associated geological features. To overcome this limitation, the authors propose a multimodal weakly supervised learning framework that leverages digital log reports to generate weak labels for fracture spacing classification and integrates these with limited human-annotated strong labels to train a fully supervised segmentation model. The approach innovatively incorporates a learnable spatial gating mechanism, combining a DINO self-supervised encoder, PiDiNet for edge detection, and Mask R-CNN for instance segmentation, alongside rule-based modules for estimating bedding angle and lithology color. Experimental results demonstrate a fracture segmentation F1 score of 0.860 (IoU 0.754), with bedding angle and lithology color predictions achieving 75.4% and 84.7% consistency, respectively, with expert log reports.
0 citationsRead paper
Recent publications
Latest Papers
Before You Poll with LLMs: A Deliberative Diagnostic Framework
本文提出了一种框架来评估LLMs在接收新信息后是否能像人类一样更新观点，通过对比模型和人类在相同信息干预后的观点变化，发现现有模型均未能准确模拟人类的观点更新。
0 citationsRead paper
A High-Throughput FPGA Architecture for Real-Time TCP-SYN Scan Detection
该研究提出了一种轻量级FPGA架构，用于实时TCP-SYN扫描检测，通过布尔LUT树并行评估指纹，实现了低延迟和高吞吐量。
0 citationsRead paper
Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation
研究探讨了量化KV缓存对检索增强生成系统忠实性的影响，使用Qwen2.5-7B-Instruct模型在不同量化级别下评估准确性和忠实性。
0 citationsRead paper
Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextualized Urdu Benchmark
研究针对低资源语言中文化不匹配导致的LLM对齐问题，通过创建首个乌尔都语3H基准Pak3H1，并采用人工校验和文化适应方法解决。
0 citationsRead paper
Automated Borehole Core Analysis with Report-Derived Weak Labels and Supervised Crack Segmentation
This study addresses the challenge posed by the absence of pixel-level fracture annotations in core images, which hinders automated extraction of fracture spacing and associated geological features. To overcome this limitation, the authors propose a multimodal weakly supervised learning framework that leverages digital log reports to generate weak labels for fracture spacing classification and integrates these with limited human-annotated strong labels to train a fully supervised segmentation model. The approach innovatively incorporates a learnable spatial gating mechanism, combining a DINO self-supervised encoder, PiDiNet for edge detection, and Mask R-CNN for instance segmentation, alongside rule-based modules for estimating bedding angle and lithology color. Experimental results demonstrate a fracture segmentation F1 score of 0.860 (IoU 0.754), with bedding angle and lithology color predictions achieving 75.4% and 84.7% consistency, respectively, with expert log reports.
0 citationsRead paper