4 citations · 8 across the 7 of their papers we have counts for
8 papers
Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog
Yiran Zhao, Shengyang Zhou, Zijian Wu +7
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources. To reduce resource c…
The Emergence of Abstract Thought in Large Language Models Beyond Any Language
Yuxin Chen, Yiran Zhao, Yang Zhang +7
As large language models (LLMs) continue to advance, their capacity to function effectively across a diverse range of languages has shown marked improvement. Preliminary studies ob…
Reasoning Robustness of LLMs to Adversarial Typographical Errors
Esther Gan, Yiran Zhao, Liying Cheng +5
Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning using Chain-of-Thought (CoT) prompting. However, CoT can be biased by users' instruction. In thi…
Self-Evaluation as a Defense Against Adversarial Attacks on LLMs
Hannah Brown, Leon Lin, Kenji Kawaguchi +1
We introduce a defense against adversarial attacks on LLMs utilizing self-evaluation. Our method requires no model fine-tuning, instead using pre-trained models to evaluate the inp…
Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models
Hongfu Liu, Yuxi Xie, Ye Wang +1
Language Language Models (LLMs) face safety concerns due to potential misuse by malicious users. Recent red-teaming efforts have identified adversarial suffixes capable of jailbrea…
Single Character Perturbations Break LLM Alignment
Leon Lin, Hannah Brown, Kenji Kawaguchi +1
When LLMs are deployed in sensitive, human-facing settings, it is crucial that they do not output unsafe, biased, or privacy-violating outputs. For this reason, models are both tra…
Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning
Yuxi Xie, Anirudh Goyal, Wenyue Zheng +4
We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process inspired by the successful s…
Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
Yiran Zhao, Wenyue Zheng, Tianle Cai +4
Safety of Large Language Models (LLMs) has become a critical issue given their rapid progresses. Greedy Coordinate Gradient (GCG) is shown to be effective in constructing adversari…