Papers by Jiashu Xu
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies on backdoor defense have focused on training phase, overlooking critical aspect of testing time defense. |
| Approach: | They propose to use demonstrations as a defense mechanism against backdoor attacks in black-box LLMs. |
| Outcome: | The proposed method outperforms existing defense baselines across most evaluation scenarios. |
Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction? (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to biomedical relation extraction (RE) are limited due to the scarcity of annotations and the prevalence of instances without explicitly pre-defined labels. |
| Approach: | They propose a method which converts biomedical relation extraction (RE) as natural language inference formulation through indirect supervision. |
| Outcome: | Extensive experiments on three widely-used biomedical RE benchmarks show that indirect supervision improves biomedically relation extraction even when a domain gap exists. |
Unified Semantic Typing with Meaningful Label Inference (2022.naacl-main)
Copied to clipboard
| Challenge: | Semantic typing aims at classifying tokens into semantic categories such as relations, entity types, and event types. |
| Approach: | They propose a unified framework for semantic typing that captures label semantics by projecting both inputs and labels into a joint semantic embedding space. |
| Outcome: | The proposed framework achieves strong performance across three semantic typing tasks. |
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | et al., 2021) show that instruction models can be trained on crowdsourced datasets with task instructions to achieve superior performance. |
| Approach: | They examine security concerns of emergent instruction tuning paradigm that models are trained on crowdsourced datasets with task instructions to achieve superior performance. |
| Outcome: | The proposed model can achieve 90% success rate across four commonly used datasets. |
Instructional Fingerprinting of Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) require considerable cost to train from scratch . fingerprinting is essential to protect intellectual property and to ensure downstream users and developers adhere to their license terms. |
| Approach: | They propose a method for fingerprinting Large language models that implants a private key into the model to generate specific text when the key is present. |
| Outcome: | The proposed method prevents publisher overclaim and maintains robustness against fingerprint guessing and parameter-efficient training. |
Securing Multi-turn Conversational Language Models From Distributed Backdoor Attacks (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have acquired the ability to handle longer context lengths and understand nuances in text, expanding their dialogue capabilities beyond a single utterance. |
| Approach: | They propose a decoding time defense that scales linearly with the input sequence length and reduces the backdoor to as low as 0.35%. |
| Outcome: | The proposed framework is generalizable, compatible with any trigger in an adversary’s toolbox in a plug-and-play manner. |