AINeutralarXiv – CS AI · May 127/10
🧠Researchers used sparse autoencoders to amplify Dark Triad personality traits in Llama-3.3-70B, demonstrating that exploitation and aggression can be isolated and amplified while deception remains unaffected. The findings reveal that antisocial behaviors in language models operate through separable computational pathways rather than unified circuits, with significant implications for AI safety monitoring and control mechanisms.
🧠 Llama
AI × CryptoBullisharXiv – CS AI · May 97/10
🤖Researchers demonstrated quantum-enhanced large language models by integrating Cayley-parameterised unitary adapters into pre-trained LLMs and executing them on IBM's 156-qubit quantum processor. The approach improved Llama 3.1 8B's perplexity by 1.4% using only 6,000 additional parameters, marking the first practical validation of quantum-classical hybrid AI on real quantum hardware at scale.
🏢 Perplexity🧠 Llama
AIBullisharXiv – CS AI · Apr 147/10
🧠Researchers identify dimensional misalignment as a critical bottleneck in compressed large language models, where parameter reduction fails to improve GPU performance due to hardware-incompatible tensor dimensions. They propose GAC (GPU-Aligned Compression), a new optimization method that achieves up to 1.5× speedup while maintaining model quality by ensuring hardware-friendly dimensions.
🧠 Llama
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers evaluated LLaMA 3.1, an open-weight large language model, for extracting structured information from Dutch brain MRI reports. The model achieved high accuracy (80-96%) on visual rating scores and detection tasks, with few-shot prompting further improving performance on numerical variables, demonstrating practical viability for automated medical data extraction in radiology.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers developed a novel safety fine-tuning method for large language models that uses the model's own outputs to identify difficult adversarial prompts, rather than relying on curated datasets. This approach significantly reduces jailbreak attack success rates on Llama models while introducing a tradeoff: increased refusal on benign prompts that resemble jailbreaks, which can be partially mitigated through mixed training strategies.
🧠 Llama
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose an improved Nash Learning from Human Feedback (NLHF) algorithm that addresses exploration challenges in preference alignment for large language models. The new method achieves better regret bounds without exponential dependence on regularization parameters and demonstrates empirical improvements when fine-tuning Llama-3-8B.
🧠 Llama
AIBullisharXiv – CS AI · Mar 176/10
🧠Researchers developed a method to control AI safety refusal behavior using categorical refusal tokens in Llama 3 8B, enabling fine-grained control over when models refuse harmful versus benign requests. The technique uses steering vectors that can be applied during inference without additional training, improving both safety and reducing over-refusal of harmless prompts.
🧠 Llama
AINeutralarXiv – CS AI · Mar 36/107
🧠Researchers propose a graph-theoretic framework for securing multi-agent LLM systems by analyzing consensus in signed, directed interaction networks. The study addresses vulnerabilities in distributed AI architectures where hidden system prompts can act as 'topological Trojan horses' that destabilize cooperative consensus among AI agents.
AINeutralHugging Face Blog · Apr 186/104
🧠The article title references Meta's release of Llama 3, their new open-source large language model. However, the article body appears to be empty, preventing detailed analysis of the announcement's specifics or implications.
