Tootfinder

ViTAD: Timing Violation-Aware Debugging of RTL Code using Large Language Models
Wenhao Lv, Yingjie Xia, Xiyuan Chen, Li Kuang
https://arxiv.org/abs/2508.13257 https://

ViTAD: Timing Violation-Aware Debugging of RTL Code using Large Language Models
In modern Very Large Scale Integrated (VLSI) circuit design flow, the Register-Transfer Level (RTL) stage presents a critical opportunity for timing optimization. Addressing timing violations at this early stage is essential, as modern systems demand higher speeds, where even minor timing violations can lead to functional failures or system crashes. However, traditional timing optimization heavily relies on manual expertise, requiring engineers to iteratively analyze timing reports and debug. T…

Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
Dongyoon Hahm, Taywon Min, Woogyeol Jin, Kimin Lee
https://arxiv.org/abs/2508.14031 https://

Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks to enhance their proficiency. However, safety concerns are frequently overlooked during this fine-tuning process. In this work, we show that aligned LLMs can become unintentionally misaligned, leading to a higher likelihood of executing harmful tasks and a red…

Red Teaming Methodology for Design Obfuscation
Yuntao Liu, Abir Akib, Zelin Lu, Qian Xu, Ankur Srivastava, Gang Qu, David Kehlet, Nij Dorairaj
https://arxiv.org/abs/2508.13965 h…

Red Teaming Methodology for Design Obfuscation
The main goal of design obfuscation schemes is to protect sensitive design details from untrusted parties in the VLSI supply chain, including but not limited to off-shore foundries and untrusted end users. In this work, we provide a systematic red teaming approach to evaluate the security of design obfuscation approaches. Specifically, we propose security metrics and evaluation methodology for the scenarios where the adversary does not have access to a working chip. A case study on the RIPPER t…

Enhanced DeepLab Based Nerve Segmentation with Optimized Tuning
Akhil John Thomas, Christiaan Boerkamp
https://arxiv.org/abs/2507.13394 https://

Enhanced DeepLab Based Nerve Segmentation with Optimized Tuning
Nerve segmentation is crucial in medical imaging for precise identification of nerve structures. This study presents an optimized DeepLabV3-based segmentation pipeline that incorporates automated threshold fine-tuning to improve segmentation accuracy. By refining preprocessing steps and implementing parameter optimization, we achieved a Dice Score of 0.78, an IoU of 0.70, and a Pixel Accuracy of 0.95 on ultrasound nerve imaging. The results demonstrate significant improvements over baseline mod…

Tuning Random Generators: Property-Based Testing as Probabilistic Programming
Ryan Tjoa, Poorva Garg, Harrison Goldstein, Todd Millstein, Benjamin Pierce, Guy Van den Broeck
https://arxiv.org/abs/2508.14394

Tuning Random Generators: Property-Based Testing as Probabilistic Programming
Property-based testing validates software against an executable specification by evaluating it on randomly generated inputs. The standard way that PBT users generate test inputs is via generators that describe how to sample test inputs through random choices. To achieve a good distribution over test inputs, users must tune their generators, i.e., decide on the weights of these individual random choices. Unfortunately, it is very difficult to understand how to choose individual generator weights…

Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models
Wuyang Zhang, Yexin Tian, Xiandong Meng, Mengjie Wang, Junliang Du
https://arxiv.org/abs/2508.14427

Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models
This paper addresses the problems of missing reasoning chains and insufficient entity-level semantic understanding in large language models when dealing with tasks that require structured knowledge. It proposes a fine-tuning algorithm framework based on knowledge graph injection. The method builds on pretrained language models and introduces structured graph information for auxiliary learning. A graph neural network is used to encode entities and their relations, constructing a graph-based sema…

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention
Amro Abdalla, Ismail Shaheen, Dan DeGenaro, Rupayan Mallick, Bogdan Raita, Sarah Adel Bargal
https://arxiv.org/abs/2507.13598

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention
We present \textbf{GIFT}: a \textbf{G}radient-aware \textbf{I}mmunization technique to defend diffusion models against malicious \textbf{F}ine-\textbf{T}uning while preserving their ability to generate safe content. Existing safety mechanisms like safety checkers are easily bypassed, and concept erasure methods fail under adversarial fine-tuning. GIFT addresses this by framing immunization as a bi-level optimization problem: the upper-level objective degrades the model's ability to represent ha…

PRIDE -- Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs
Maluna Menke, Thilo Hagendorff
https://arxiv.org/abs/2507.13743 http…

PRIDE -- Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs
Large Language Models (LLMs) frequently reproduce the gender- and sexual-identity prejudices embedded in their training corpora, leading to outputs that marginalize LGBTQIA+ users. Hence, reducing such biases is of great importance. To achieve this, we evaluate two parameter-efficient fine-tuning (PEFT) techniques - Low-Rank Adaptation (LoRA) and soft-prompt tuning - as lightweight alternatives to full-model fine-tuning for mitigating such biases. Using the WinoQueer benchmark, we quantify bias…

Saudi-Dialect-ALLaM: LoRA Fine-Tuning for Dialectal Arabic Generation
Hassan Barmandah
https://arxiv.org/abs/2508.13525 https://arxiv.org/pdf/2508.13525

Saudi-Dialect-ALLaM: LoRA Fine-Tuning for Dialectal Arabic Generation
Large language models (LLMs) for Arabic are still dominated by Modern Standard Arabic (MSA), with limited support for Saudi dialects such as Najdi and Hijazi. This underrepresentation hinders their ability to capture authentic dialectal variation. Using a privately curated Saudi Dialect Instruction dataset (Hijazi and Najdi; 5,466 synthetic instruction-response pairs; 50/50 split), we LoRA-tune ALLaM-7B-Instruct-preview, the first foundation model developed in Saudi Arabia, for Saudi dialect ge…

The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation
Shubham Pundhir, Ganesh Bagler
https://arxiv.org/abs/2508.14718 https://…

The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation
We established a rigorous benchmark for text-based recipe generation, a fundamental task in natural language generation. We present a comprehensive comparative study contrasting a fine-tuned GPT-2 large (774M) model against the GPT-2 small (124M) model and traditional LSTM/RNN baselines on the 5-cuisine corpus from RecipeDB. Our key contribution is a targeted tokenization strategy that augments the vocabulary with 23 common fraction tokens and custom structural markers. This approach addresses …