8 papers
FlipAttack: Jailbreak LLMs via Flipping
Yue Liu, Xiaoxin He, Miao Xiong +5
This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we reveal that LLMs tend to understand t…
TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering
Yuan Sui, Yulin Chen, Yibo Li +6
When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure…
Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation
Mufei Li, Dongqi Fu, Limei Wang +10
Modern long-context large language models (LLMs) perform well on synthetic "needle-in-a-haystack" (NIAH) benchmarks, but such tests overlook how noisy contexts arise from biased re…
FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
Yuan Sui, Yufei He, Nian Liu +3
Large Language Models (LLMs) are often challenged by generating erroneous or hallucinated responses, especially in complex reasoning tasks. Leveraging Knowledge Graphs (KGs) as ext…
A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition
Nian Liu, Xiaoxin He, Thomas Laurent +3
Spectral graph convolution, an important tool of data filtering on graphs, relies on two essential decisions: selecting spectral bases for signal transformation and parameterizing…
UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs
Yufei He, Yuan Sui, Xiaoxin He +3
Existing foundation models, such as CLIP, aim to learn a unified embedding space for multimodal data, enabling a wide range of downstream web-based applications like search, recomm…