2024
pdf
abs
Fake Alignment: Are LLMs Really Aligned Well?
Yixu Wang
|
Yan Teng
|
Kexin Huang
|
Chengqi Lyu
|
Songyang Zhang
|
Wenwei Zhang
|
Xingjun Ma
|
Yu-Gang Jiang
|
Yu Qiao
|
Yingchun Wang
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial discrepancy in performance between multiple-choice questions and open-ended questions. Inspired by research on jailbreak attack patterns, we argue this is caused by mismatched generalization. That is, LLM only remembers the answer style for open-ended safety questions, which makes it unable to solve other forms of safety tests. We refer to this phenomenon as fake alignment and construct a comparative benchmark to empirically verify its existence in LLMs. We introduce a Fake alIgNment Evaluation (FINE) framework and two novel metrics——Consistency Score (CS) and Consistent Safety Score (CSS), which jointly assess two complementary forms of evaluation to quantify fake alignment and obtain corrected performance estimation. Applying FINE to 14 widely-used LLMs reveals several models with purported safety are poorly aligned in practice. Subsequently, we found that multiple-choice format data can also be used as high-quality contrast distillation-based fine-tuning data, which can strongly improve the alignment consistency of LLMs with minimal fine-tuning overhead. For data and code, see https://github.com/AIFlames/Fake-Alignment.
pdf
abs
AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
Jun Zhan
|
Junqi Dai
|
Jiasheng Ye
|
Yunhua Zhou
|
Dong Zhang
|
Zhigeng Liu
|
Xin Zhang
|
Ruibin Yuan
|
Ge Zhang
|
Linyang Li
|
Hang Yan
|
Jie Fu
|
Tao Gui
|
Tianxiang Sun
|
Yu-Gang Jiang
|
Xipeng Qiu
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music. AnyGPT can be trained stably without any alterations to the current large language model (LLM) architecture or training paradigms. Instead, it relies exclusively on data-level preprocessing, facilitating the seamless integration of new modalities into LLMs, akin to the incorporation of new languages.We build a multimodal text-centric dataset for multimodal alignment pre-training. Utilizing generative models, we synthesize the first large-scale any-to-any multimodal instruction dataset. It consists of 108k samples of multi-turn conversations that intricately interweave various modalities, thus equipping the model to handle arbitrary combinations of multimodal inputs and outputs.Experimental results demonstrate that AnyGPT is capable of facilitating any-to-any multimodal conversation while achieving performance comparable to specialized models across all modalities, proving that discrete representations can effectively and conveniently unify multiple modalities within a language model. Demos are shown in https://junzhan2000.github.io/AnyGPT.github.io/.
2018
pdf
abs
Cross-Domain Sentiment Classification with Target Domain Specific Information
Minlong Peng
|
Qi Zhang
|
Yu-gang Jiang
|
Xuanjing Huang
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
The task of adopting a model with good performance to a target domain that is different from the source domain used for training has received considerable attention in sentiment analysis. Most existing approaches mainly focus on learning representations that are domain-invariant in both the source and target domains. Few of them pay attention to domain-specific information, which should also be informative. In this work, we propose a method to simultaneously extract domain specific and invariant representations and train a classifier on each of the representation, respectively. And we introduce a few target domain labeled data for learning domain-specific information. To effectively utilize the target domain labeled data, we train the domain invariant representation based classifier with both the source and target domain labeled data and train the domain-specific representation based classifier with only the target domain labeled data. These two classifiers then boost each other in a co-training style. Extensive sentiment analysis experiments demonstrated that the proposed method could achieve better performance than state-of-the-art methods.