Suffix Prediction

Suffix prediction focuses on accurately forecasting the remaining sequence of events or tokens in a given context, a problem relevant to diverse fields from natural language processing to process mining. Current research emphasizes improving the efficiency and accuracy of prediction, exploring techniques like encoder-decoder models with attention mechanisms, and employing gradient-based optimization methods to generate or control suffixes, often within the context of mitigating adversarial attacks or enhancing large language model safety. These advancements have implications for improving the reliability and safety of AI systems, as well as optimizing resource allocation and prediction accuracy in various operational contexts.

Papers

November 13, 2024

LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs
Piyush Jha, Arnav Arora, Vijay Ganesh
Medical LLM Jailbreak Attack Adversarial Suffix LLM Attack Suffix Prediction

November 7, 2024

SuffixDecoding: A Model-Free Approach to Speeding Up Large Language Model Inference
Gabriele Oliaro, Zhihao Jia, Daniel Campos, Aurick Qiao
Large Language Model Free Speculative Decoding Model Inference Suffix Prediction

October 29, 2024

AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts
Vishal Kumar, Zeyi Liao, Jaylen Jones, Huan Sun
Large Language Model Generative Model Adversarial Suffix Suffix Prediction

October 16, 2024

Parsing Akkadian Verbs with Prolog
Aaron Macks
Suffix Prediction Finite Data SWI Prolog Cuneiform Tablet

August 21, 2024

Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer
Weipeng Jiang, Zhenting Wang, Juan Zhai, Shiqing Ma, Zhengyu Zhao, Chao Shen
Medical LLM Jailbreak Attack Superior Optimizer Attack Performance Adversarial Suffix Token Optimization Suffix Prediction

July 16, 2024

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
Zihao Xu, Yi Liu, Gelei Deng, Kailong Wang, Yuekang Li, Ling Shi, Stjepan Picek
Large Language Model Jailbreak Attack New Attack Continuous Speech Discrete Prompt Suffix Prediction Continuous Embeddings

June 4, 2024

Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller
Min Cai, Yuchen Zhang, Shichang Zhang, Fan Yin, Dan Zhang, Difan Zou, Yisong Yue, Ziniu Hu
Large Language Model LLM Behavior Auto Regressive Generation Suffix Prediction Meta Controller Self Restraint

March 5, 2024

Word Importance Explains How Prompts Affect Language Model Outputs
Stefan Hackmann, Haniyeh Mahmoudian, Mark Steadman, Michael Schmidt
Large Language Model Language Model Suffix Prediction Word Importance

December 9, 2023

Enhancing the Accuracy of Predictors of Activity Sequences of Business Processes
Muhammad Awais Ali, Marlon Dumas, Fredrik Milani
Predictive Model Business Process Predictive Process Monitoring Activity Sequence Suffix Prediction

October 20, 2023

An Event based Prediction Suffix Tree
Evie Andrew, Travis Monk, André van Schaik
Anomaly Detection Event Description Event Sequence Suffix Prediction

July 10, 2023

Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation
Zhexin Zhang, Jiaxin Wen, Minlie Huang
Pre Trained Language Model Large Pre Trained Language Model Intercultural Ethic Calibrated Confidence Suffix Prediction Training Data Extraction

March 26, 2023

Koala: An Index for Quantifying Overlaps with Pre-training Corpora
Thuy-Trang Vu, Xuanli He, Gholamreza Haffari, Ehsan Shareghi
Large Corpus Pre Training Training Corpus Pre Training Corpus Index Decomposition Suffix Prediction

November 29, 2022

Encoder-Decoder Model for Suffix Prediction in Predictive Monitoring
Efrén Rama-Maneiro, Pablo Monteagudo-Lago, Juan C. Vidal, Manuel Lama
Process Mining Encoder Decoder Model Predictive Monitoring Suffix Prediction

November 6, 2022

Suffix Retrieval-Augmented Language Modeling
Zecheng Wang, Yik-Cheung Tam
Language Model Retrieval Augmented Language Model Causal Language Bidirectional Correspondence Suffix Prediction

Suffix Prediction

Papers

LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs

SuffixDecoding: A Model-Free Approach to Speeding Up Large Language Model Inference

AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts

Parsing Akkadian Verbs with Prolog

Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models

Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller

Word Importance Explains How Prompts Affect Language Model Outputs

Enhancing the Accuracy of Predictors of Activity Sequences of Business Processes

An Event based Prediction Suffix Tree

Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation

Koala: An Index for Quantifying Overlaps with Pre-training Corpora

Encoder-Decoder Model for Suffix Prediction in Predictive Monitoring

Suffix Retrieval-Augmented Language Modeling