5 papers
ParaTempo: Efficient Parallel Reasoning via Temporal Confidence
Xuteng Zhang, Wenhao Zeng, Xiaodong Gu +5
Parallel reasoning improves the accuracy and robustness of large reasoning models by exploring multiple solution paths, but its computational cost grows with reasoning depth and br…
Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agents
Xiang Chen, Yuling Shi, Qizhen Lan +4
LLM agents are widely deployed in complex interactive tasks, yet privacy constraints often preclude centralized optimization and co-evolution across dynamic environments. Despite t…
Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!
Do-hyeon Yoon, Minsoo Chun, Thomas Allen +3
Large language models (LLMs) face significant copyright and intellectual property challenges as the cost of training increases and model reuse becomes prevalent. While watermarking…
LastingBench: Defend Benchmarks Against Knowledge Leakage
Yixiong Fang, Tianran Sun, Yuling Shi +2
The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific…
Token-Efficient Leverage Learning in Large Language Models
Yuanhao Zeng, Min Wang, Yihang Wang +1
Large Language Models (LLMs) have excelled in various tasks but perform better in high-resource scenarios, which presents challenges in low-resource scenarios. Data scarcity and th…