Papers by Victor Rühle

4 papers
TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning (2025.findings-acl)

Copied to clipboard

Challenge: Existing prompt compression techniques rely on sub-optimal metrics such as information entropy or model it as a task-agnostic token classification problem that fails to capture task-specific information.
Approach: They propose a task-aware prompt compression method that leverages existing Transformer encoders and a lightweight REINFORCE algorithm to ensure low latency requirements.
Outcome: The proposed method improves task performance by 8% - 189% on three diverse and challenging tasks over state-of-the-art techniques while satisfying the same compression rate and latency requirements.
Hybrid-RACA: Hybrid Retrieval-Augmented Composition Assistance for Real-time Text Prediction (2024.emnlp-industry)

Copied to clipboard

Challenge: Large language models (LLMs) enhanced with retrieval augmentation have shown great performance in many applications, but their computational overhead and additional retrieval step limit their effectiveness in real-time tasks.
Approach: They propose a system that combines a cloud-based LLM with a smaller client-side model through retrieval augmented memory to provide real-time text prediction.
Outcome: The proposed system can generate better responses from the cloud-based model while maintaining low latency.
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression (2024.findings-acl)

Copied to clipboard

Challenge: Existing approaches to compress prompts only leverage unidirectional context, causing suboptimal results.
Approach: They propose a task-agnostic prompt compression method that takes tokens from context . they use a Transformer encoder to capture all essential information needed for prompt compression .
Outcome: The proposed method is 3x-6x faster than existing prompt compression methods and faster than baselines.
Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels (2021.naacl-main)

Copied to clipboard

Challenge: Neural language models have a high capacity for memorization of training samples . however, this can cause privacy degradation and disparate impact on subgroups of users .
Approach: They propose two privacy-preserving regularization methods for training language models that enable joint optimization of utility and privacy.
Outcome: The proposed methods have favorable utility-privacy trade-off, faster training and uniform treatment of under-represented subgroups.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations