6 citations · 22 across the 15 of their papers we have counts for
12 papers · 1 filter
Improving Your Model Ranking on Chatbot Arena by Vote Rigging
Rui Min, Tianyu Pang, Chao Du +3
Chatbot Arena is a popular platform for evaluating LLMs by pairwise battles, where users vote for their preferred response from two randomly sampled anonymous models. While Chatbot…
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
Haonan Wang, Qian Liu, Chao Du +4
Extending context window sizes allows large language models (LLMs) to process longer sequences and handle more complex tasks. Rotary Positional Embedding (RoPE) has become the de f…
When Attention Sink Emerges in Language Models: An Empirical View
Xiangming Gu, Tianyu Pang, Chao Du +5
Language Models (LMs) assign significant attention to the first token, even if it is not semantically important, which is known as attention sink. This phenomenon has been widely a…
Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates
Xiaosen Zheng, Tianyu Pang, Chao Du +3
Automatic LLM benchmarks, such as AlpacaEval 2.0, Arena-Hard-Auto, and MT-Bench, have become popular for evaluating language models due to their cost-effectiveness and scalability…
Bootstrapping Language Models with DPO Implicit Rewards
Changyu Chen, Zichen Liu, Chao Du +5
Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the proces…
Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
Xuan Zhang, Chao Du, Tianyu Pang +3
The recent development of chain-of-thought (CoT) decoding has enabled large language models (LLMs) to generate explicit logical reasoning paths for complex problem-solving. However…
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
Xiaosen Zheng, Tianyu Pang, Chao Du +3
Recently, Anil et al. (2024) show that many-shot (up to hundreds of) demonstrations can jailbreak state-of-the-art LLMs by exploiting their long-context capability. Nevertheless, i…
Sailor: Open Language Models for South-East Asia
Longxu Dou, Qian Liu, Guangtao Zeng +4
We present Sailor, a family of open language models ranging from 0.5B to 7B parameters, tailored for South-East Asian (SEA) languages. These models are continually pre-trained from…
Purifying Large Language Models by Ensembling a Small Language Model
Tianlin Li, Qian Liu, Tianyu Pang +4
The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to d…
Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One
Tianlin Li, Xiaoyu Zhang, Chao Du +5
The widespread adoption of large language models (LLMs) underscores the urgent need to ensure their fairness. However, LLMs frequently present dominant viewpoints while ignoring al…
Test-Time Backdoor Attacks on Multimodal Large Language Models
Dong Lu, Tianyu Pang, Chao Du +3
Backdoor attacks are commonly executed by contaminating training data, such that a trigger can activate predetermined harmful effects during the test phase. In this work, we presen…
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
Xiangming Gu, Xiaosen Zheng, Tianyu Pang +5
A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming eff…