Papers with reverse alignment
Alirector: Alignment-Enhanced Chinese Grammatical Error Corrector (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to address overcorrection in Chinese grammatical error correction (CGEC) are difficult to adapt to decoder-only large language models (LLMs). |
| Approach: | They propose an alignment-enhanced corrector for the overcorrection problem that applies to both Seq2Seq models and decoder-only large language models (LLMs). |
| Outcome: | The proposed corrector alleviates the overcorrection problem in Chinese grammatical error correction (CGEC) using generative models and decoder-only large language models. |
On the Vulnerability of Safety Alignment in Open-Access LLMs (2024.findings-acl)
Copied to clipboard
Jingwei Yi, Rui Ye, Qisi Chen, Bin Zhu, Siheng Chen, Defu Lian, Guangzhong Sun, Xing Xie, Fangzhao Wu
| Challenge: | Large language models (LLMs) are susceptible to malicious exploitation, but are often rejected and limited harmfulness is limited. |
| Approach: | They propose two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO). |
| Outcome: | The proposed methods can significantly enhance the success rate and harmfulness of jailbreak attacks, but they face high rejection rates and limited harmfulness. |