unbiarirang / Fixed-Input-Parameterization
This repository contains the official code for the paper: "Prompt Injection: Parameterization of Fixed Inputs"
☆32Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for Fixed-Input-Parameterization
- Restore safety in fine-tuned language models through task arithmetic☆26Updated 7 months ago
- [NeurIPS 2022 Workshop] A Case Study with Negated Prompts using T0 (3B, 11B), InstructGPT (350M-175B), GPT-3 (350M - 175B) & OPT (125M - …☆23Updated 2 years ago
- ☆24Updated last year
- ☆44Updated 2 months ago
- [EMNLP Findings 2024 & ACL 2024 NLRSE Oral] Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards☆44Updated 6 months ago
- Code for "Universal Adversarial Triggers Are Not Universal."☆16Updated 6 months ago
- ☆16Updated last year
- ☆11Updated 2 years ago
- DEMix Layers for Modular Language Modeling☆53Updated 3 years ago
- ☆26Updated 8 months ago
- Methods and evaluation for aligning language models temporally☆24Updated 8 months ago
- ☆13Updated 2 years ago
- TBC☆26Updated 2 years ago
- Code for "Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning" (EMNLP 2022) and "Empowering Parameter-Efficient Transfer Learning…☆11Updated last year
- ☆22Updated 2 years ago
- [EMNLP 2023 Findings] Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt☆20Updated last year
- ☆48Updated last year
- ☆40Updated 11 months ago
- [NeurIPS 2022] Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings☆20Updated last year
- [ICML 2023] Exploring the Benefits of Training Expert Language Models over Instruction Tuning☆97Updated last year
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆47Updated 4 months ago
- Grade-School Math with Irrelevant Context (GSM-IC) benchmark is an arithmetic reasoning dataset built upon GSM8K, by adding irrelevant se…☆55Updated last year
- ☆23Updated 11 months ago
- [EMNLP 2022] TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models☆66Updated 6 months ago
- [EMNLP-2022 Findings] Code for paper “ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback”.☆24Updated last year
- Generating diverse counterfactual data for Natural Language Understanding tasks using Large Language Models (LLMs). The generator support…☆35Updated last year
- Visual and Embodied Concepts evaluation benchmark☆21Updated last year
- [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models☆76Updated 2 months ago
- ☆33Updated last year
- Data Valuation on In-Context Examples (ACL23)☆23Updated last month