llms

Documents about llms

• LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling#172745Papers With Code
• LLMs and Meaning: what the current semantic challenges in LLMs highlight about Natural Language#705051PhilArchive
• Relational Growth in Static LLMs: Why LLMs Can Appear to “Grow” Through Human-AI Interaction#79373PhilArchive
• Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond#282718arXiv CS
• Do LLMs Really Represent the World? A Teleosemantic Assessment of Pre-Trained, Fine-Tuned, and Agentic LLMs#693500PhilArchive
• LLMs, Descriptivism, and Structuralism#691608PhilArchive
• Should Healthcare Resist AI?: The Transformative Impact of LLMs in Digital Pathology#318996IRIS
• Request routing services undermine the reproducibility of open weight LLMs#428546OSF
• Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs#126562arXiv CS
• LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context#303277arXiv CS
• How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair#411126arXiv CS
• LLMs are not Artificial intelligence#95494PhilArchive
• Suppressing Hallucination for Trustworthy LLMs#98950PhilArchive
• Indagación estructurada en LLMs#112153PhilArchive
• Factuality Beyond Reference in LLMs#691014PhilArchive
• LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs#259527arXiv CS
• Automatic or Controlled? Repetition Priming Reveals Divergent Processing in Base LLMs, Instruct LLMs, and Humans#609116arXiv (OAI Expanded)
• Can LLMs Understand the Impact of Trauma? Costs and Benefits of LLMs Coding the Interviews of Firearm Violence Survivors#31313arXiv CS
• <b>Prompting with Empathy: Persona-Guided Requirement Generation Using LLMs (Suplementary Materials)</b>#196688Figshare
• Privacy-Preserving LLMs Routing#31211arXiv CS
• LLMs Can Never Be Ideally Rational#112524PhilArchive
• A Study on the Performance of SOTA LLMs on Nepalese IOE Entrance Examination#405802HAL (France)
• Revealing life preferences through LLMs#300540EconStor
• Language and thought: The view from LLMs#17600PhilArchive
• LLMs and the Problem of Uncommon Ground#75312PhilArchive
• CryptanalysisBench: Can LLMs do Cryptanalysis?#386754arXiv CS
• Can LLMs Acquire Human-Like World Models?#687545PhilArchive
• Are LLMs In-Between Believers?#695337PhilArchive
• Theory of mind beyond beliefs: Testing attention-based social micro-processes in LLMs#397112OSF
• A Hyper-Externalist Manifesto for LLMs#83572PhilArchive
• Sapience without Sentience: An Inferentialist Approach to LLMs#115042PhilArchive
• Do LLMs have core beliefs?#119168PhilArchive
• Diagnosing CFG Interpretation in LLMs#124079arXiv CS
• FloatDoor: Platform-Triggered Backdoors in LLMs#290539arXiv CS
• Qiskit Code Migration with LLMs#290641arXiv CS
• Do LLMs Know Their Vulnerable Scenarios?#405568arXiv CS
• Generating Attacks for LLMs with GFlowNets#444582arXiv CS
• Redakto - The Incognito Tab for LLMs#467093arXiv CS
• Competitive Market Behavior of LLMs#632876arXiv CS
• Benchmarking LLMs for Threat Level Determination#667928arXiv CS
• No Epistemic Respect for Bullshit Machines or LLMs#700064PhilArchive
• If it bleeds, it leads? Evaluating whether LLMs can identify what is newsworthy#457874OSF
• Language Writ Large: LLMs, ChatGPT, Grounding, Meaning and Understanding#17460PhilArchive
• DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy#31205arXiv CS
• Bridging the Divide: Using LLMs to Reshape Difficult Disagreements#71473PhilArchive
• Pseudo-Self_Language-Based_Formation_and_Collapse_in_LLMs#86174PhilArchive
• Standards for Belief Representations in LLMs#94193PhilArchive
• Interpreting LLMs: Challenges to a Knowledge-First Approach#96534PhilArchive
• What lies behind AGI: ethical concerns related to LLMs#99835PhilArchive
• CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge#123958arXiv CS