반응형 전체 글599 [2023-09-17] 오늘의 자연어처리 Tree of Uncertain Thoughts Reasoning for Large Language Models Abstract:While the recently introduced Tree of Thoughts (ToT) has heralded advancements in allowing Large Language Models (LLMs) to reason through foresight and backtracking for global decision-making, it has overlooked the inherent local uncertainties in intermediate decision points or "thoughts". These local uncertainties, intrinsi.. 2023. 9. 17. [2023-09-16] 오늘의 자연어처리 Ambiguity-Aware In-Context Learning with Large Language Models Abstract:In-context learning (ICL) i.e. showing LLMs only a few task-specific demonstrations has led to downstream gains with no task-specific fine-tuning required. However, LLMs are sensitive to the choice of prompts, and therefore a crucial research question is how to select good demonstrations for ICL. One effective strategy is le.. 2023. 9. 16. [2023-09-15] 오늘의 자연어처리 Native Language Identification with Big Bird Embeddings Native Language Identification (NLI) intends to classify an author's native language based on their writing in another language. Historically, the task has heavily relied on time-consuming linguistic feature engineering, and transformer-based NLI models have thus far failed to offer effective, practical alternatives. The current work invest.. 2023. 9. 15. [2023-09-14] 오늘의 자연어처리 Circuit Breaking: Removing Model Behaviors with Targeted Ablation Language models often exhibit behaviors that improve performance on a pre-training objective but harm performance on downstream tasks. We propose a novel approach to removing undesirable behaviors by ablating a small number of causal pathways between model components, with the intention of disabling the computational circuit respo.. 2023. 9. 14. 이전 1 ··· 26 27 28 29 30 31 32 ··· 150 다음 반응형