Cover Image

Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xinze, Liu, Zhenghao, Xiong, Chenyan, Yu, Shi, Yan, Yukun, Wang, Shuo, Yu, Ge
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
by: Li, Xinze, et al.
Published: (2024)

Cleaner Pretraining Corpus Curation with Neural Web Scraping
by: Xu, Zhipeng, et al.
Published: (2024)

Learning to Compress Prompts with Gist Tokens
by: Mu, Jesse, et al.
Published: (2023)

HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization
by: Wang, Haolan, et al.
Published: (2025)

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts
by: Wu, Mingyan, et al.
Published: (2025)

Building A Coding Assistant via the Retrieval-Augmented Language Model
by: Li, Xinze, et al.
Published: (2024)

MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization
by: Xin, Haidong, et al.
Published: (2026)

ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling
by: Xu, Zhipeng, et al.
Published: (2024)

Structured Knowledge Representation through Contextual Pages for Retrieval-Augmented Generation
by: Li, Xinze, et al.
Published: (2026)

Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
by: Liu, Zhenghao, et al.
Published: (2026)

Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection
by: Wu, Zhuoyang, et al.
Published: (2025)

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization
by: Jin, Zhensheng, et al.
Published: (2025)

Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
by: Liu, Shuliang, et al.
Published: (2025)

Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
by: Duan, Shaohua, et al.
Published: (2025)

Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model
by: Qian, Cheng, et al.
Published: (2023)

Compressing Lengthy Context With UltraGist
by: Zhang, Peitian, et al.
Published: (2024)

Legal$Δ$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
by: Dai, Xin, et al.
Published: (2025)

Craw4LLM: Efficient Web Crawling for LLM Pretraining
by: Yu, Shi, et al.
Published: (2025)

Finding What Matters: Anchoring Context Knowledge with Evolving Indices for Iterative Retrieval
by: Wu, Mingyan, et al.
Published: (2026)

LegalDuet: Learning Fine-grained Representations for Legal Judgment Prediction via a Dual-View Contrastive Learning
by: Xu, Buqiang, et al.
Published: (2024)

Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling
by: Liu, Shuliang, et al.
Published: (2025)

Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
by: Peng, Chunyi, et al.
Published: (2025)

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
by: Huang, Pengcheng, et al.
Published: (2025)

Sentence-Anchored Gist Compression for Long-Context LLMs
by: Tarasov, Dmitrii, et al.
Published: (2025)

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
by: Deng, Chenlong, et al.
Published: (2025)

What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts
by: Yang, Chenyang, et al.
Published: (2025)

GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
by: Gupta, Shivanshu, et al.
Published: (2023)

RePro: Training Language Models to Faithfully Recycle the Web for Pretraining
by: Yu, Zichun, et al.
Published: (2025)

When More Words Say Less: Decoupling Length and Specificity in Image Description Evaluation
by: Kapur, Rhea, et al.
Published: (2026)

Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning
by: Li, Xiaochuan, et al.
Published: (2024)

See or Say Graphs: Agent-Driven Scalable Graph Structure Understanding with Vision-Language Models
by: Han, Shuo, et al.
Published: (2025)

Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation
by: Riaz, Haris, et al.
Published: (2025)

EmoGist: Efficient In-Context Learning for Visual Emotion Understanding
by: Seoh, Ronald, et al.
Published: (2025)

Understand Then Memory: A Cognitive Gist-Driven RAG Framework with Global Semantic Diffusion
by: Zhou, Pengcheng, et al.
Published: (2026)

Generating Pretraining Tokens from Organic Data for Data-Bound Scaling
by: Yu, Zichun, et al.
Published: (2026)

A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression
by: Deng, Chenlong, et al.
Published: (2024)

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation
by: Chen, Hao, et al.
Published: (2025)

Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding
by: Bao, Jianzhu, et al.
Published: (2026)

Less Is More: Elevating RAG via Performance-Driven Context Compression
by: Cui, Ziqiang, et al.
Published: (2025)

AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning
by: Wang, Tevin, et al.
Published: (2025)