paper-with-me

Papers

Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories

2021-09-08 · EMNLP 2021 11 · David Wilmot, Frank Keller

Measuring event salience is essential in the understanding of stories. This paper takes a recent unsupervised method for salience detection derived from Barthes Cardinal Functions and theories of surprise and applies it to longer narrative forms. We improve the standard transformer language model by incorporating an external knowledgebase (derived from Retrieval Augmented Generation) and adding a memory mechanism to enhance performance on longer works. We use a novel approach to derive salience annotation using chapter-aligned summaries from the Shmoop corpus for classic literary works. Our evaluation against this data demonstrates that our salience detection model improves performance over and above a non-knowledgebase and memory augmented language model, both of which are crucial to this improvement.

📄 PDF Abstract BibTeX arXiv:2109.03754

Code (1)

dwlmt/story-fragments 공식 구현 pytorch

Tasks

FormLanguage ModelingLanguage ModellingRetrievalRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

Selective Memory for Artificial Intelligence: Write-Time Gating with Hierarchical Archiving

2026-03-16 · Oliver Zahn, Simran Chana arxiv

Retrieval-augmented generation stores all content indiscriminately, degrading accuracy as noise accumulates. Parametric approaches compress knowledge into weights, precluding selective updates. Neither mirrors biological…

REMI: A Novel Causal Schema Memory Architecture for Personalized Lifestyle Recommendation Agents

2025-09-08 · Vishal Raman, Vijai Aravindh R, Abhijith Ragav arxiv

Personalized AI assistants often struggle to incorporate complex personal data and causal knowledge, leading to generic advice that lacks explanatory power. We propose REMI, a Causal Schema Memory architecture for a mult…

SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

2024-05-23 · Wei Huang, Haotong Qin, Yangdong Liu, Yawei Li 외

Large language models (LLMs) achieve remarkable performance in natural language understanding but require substantial computation and memory resources. Post-training quantization (PTQ) is a powerful compression technique…

Natural Language UnderstandingQuantization

MemoBrain: Executive Memory as an Agentic Brain for Reasoning

2026-01-12 · Hongjin Qian, Zhao Cao, Zheng Liu arxiv

Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working context of large language models. Withou…

Contrastive Learning with Narrative Twins for Modeling Story Salience

2026-01-12 · Igor Sterner, Alex Lascarides, Frank Keller arxiv

Understanding narratives requires identifying which events are most salient for a story's progression. We present a contrastive learning framework for modeling narrative salience that learns story embeddings from narrati…

Contrastive Learning