Papers by Zhiyu Xu

11 papers
Dictionary Guided Sparse Logit Editing for Reliable Jailbreak Attacks (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods to optimize large language models suffer from high computational costs and produce uninterpretable, high-perplexity inputs.
Approach: They propose a sparse index-based intervention that bypasses guardrails via sparser logit editing.
Outcome: The proposed method bypasses guardrails by modifying pre-softmax logits without gradients or auxiliary models.
FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information.
Approach: They propose a method to enhance LLMs' context awareness by updating only the last Feed-Forward Network module to maximize the likelihood of the prompt before inference .
Outcome: The proposed method improves the accuracy of Llama 3-8B-Inst on the NQ-SWAP dataset from 59.1% to 71.6% and reduces the output structure failure rate of Qwen 1.5-4B-Chat from 34.9% to 25.5%.
StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding (2026.findings-acl)

Copied to clipboard

Challenge: StreamMeCo is an efficient Stream Agent Memory Compression framework for video understanding.
Approach: They propose an efficient Stream Agent Memory Compression framework that evicts redundant memory nodes and introduces a time-decay memory retrieval mechanism to mitigate performance degradation.
Outcome: The proposed framework achieves 1.87 speedup in memory retrieval while delivering an average accuracy improvement of 1.0% on three challenging benchmark datasets.
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)

Copied to clipboard

Challenge: Scientific data visualization is an essential process in research, but its use of large language models remains unexplored.
Approach: They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks.
Outcome: The proposed framework improves performance of commercial and open-source models.
Defending LLMs against Jailbreak Attacks via Template-Based ICL with a Defensive Suffix (2026.findings-acl)

Copied to clipboard

Challenge: State-of-the-art large language models (LLMs) are vulnerable to jailbreak attacks, such as GCG and AutoDAN.
Approach: They propose to take the advances of online In-Context Learning and an offline defensive suffix and optimize them using an iterative algorithm and an online stochastic random search to identify the most effective ICL demonstrations.
Outcome: The proposed method reduces attack success rate to nearly *0% while maintaining the model’s utility on benign tasks and incurring only *negligible* computational overhead.
Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters (2026.acl-long)

Copied to clipboard

Challenge: Existing research lacks systematic analysis of the applicability and methodology of cross-modal skill injection.
Approach: They investigate the applicability and methodology of cross-modal skill injection by integrating a domain-expert LLM into a VLM.
Outcome: The proposed method enables transfer of domain-specific expertise from Large Language Models (LLMs) to VLMs without incurring additional training data requirements or significant computational overhead.
Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction (2021.findings-acl)

Copied to clipboard

Challenge: Distantly supervised relation extraction (RE) has attracted much attention in the past few years . previous methods to evaluate models manually or directly on autolabeled data have produced inaccurate evaluations .
Approach: They propose to use distant supervision to generate large-scale autolabeled data . they build manually-annotated test sets for two DS-RE datasets and evaluate models .
Outcome: The proposed method produces 53% wrong labels at the entity pair level in the popular NYT10 dataset.
Text2Mem: A Unified Memory Operation Language for Memory Operating System (2026.findings-acl)

Copied to clipboard

Challenge: Existing memory frameworks lack a formal, executable specification for memory control.
Approach: They propose a unified memory operation language that standardizes translation of natural-language instructions into reliable execution.
Outcome: The proposed language standardizes translation of natural-language instructions into reliable execution.
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset (2024.acl-long)

Copied to clipboard

Challenge: Open-source large language models (LLMs) have gained strength across diverse fields, but the majority of studies focus on English.
Approach: They propose a knowledge-grounded data augmentation approach to elicit more language-specific knowledge of LLMs by enhancing their ability to serve users from different countries.
Outcome: The proposed method can prune the language-agnostic supervised fine-tuning dataset without any performance degradation.
NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing conversational systems are agent-centric, which assumes the user utterances will closely follow the system ontology.
Approach: They build a dataset that maps user preferences to an ontology and model user preferences as estimated distributions over the system ontologies.
Outcome: The proposed system can be used to push existing research from agent-centric to user-centric.
Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems (2026.acl-long)

Copied to clipboard

Challenge: Existing personalized dialogue systems struggle to reconcile unbounded interactions with finite context constraints.
Approach: They propose a framework that utilizes a globally maintained PersonaTree as the carrier of long-term user profiling.
Outcome: The proposed framework outperforms existing systems in suppressing contextual noise and persona inconsistency.

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