[QA] Beyond position: how rotary embeddings shape representations andmemory in transfomers Arxiv Papers 7,92 тыс. подписчиков Скачать
Beyond position: how rotary embeddings shape representations andmemory in autoregressive transfomers Скачать
[QA] Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs Скачать
[QA] Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs Скачать
[QA] GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models Скачать
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models Скачать
[QA] Density estimation with LLMs: a geometric investigation of in-context learning trajectories Скачать
[QA] Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models Скачать
Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts Скачать
[QA] Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts Скачать
[QA] Re-Introducing LayerNorm: Geometric Meaning, Irreversibility and Comparative Study with RMSNorm Скачать
Re-Introducing LayerNorm: Geometric Meaning, Irreversibility and a Comparative Study with RMSNorm Скачать
[QA] PingPong: A Benchmark for Role-Playing LLMs with User Emulation and Multi-Model Evaluation Скачать
[QA] Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers Скачать
[QA] SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection Скачать
SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection Скачать