thu-coai / Implicit-ToxicityLinks
Official Code for EMNLP 2023 paper: "Unveiling the Implicit Toxicity in Large Language Models""
☆13Updated last year
Alternatives and similar repositories for Implicit-Toxicity
Users that are interested in Implicit-Toxicity are comparing it to the libraries listed below
Sorting:
- ☆75Updated 6 months ago
- ☆10Updated last year
- This repo is for the paper: On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark☆25Updated 2 years ago
- ☆13Updated last year
- Unofficial re-implementation of "Trusting Your Evidence: Hallucinate Less with Context-aware Decoding"☆30Updated 7 months ago
- Official Code for EMNLP2023 Main Conference paper: "KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detec…☆30Updated last year
- EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data" https://arxiv.org/abs/2210.14975☆38Updated last year
- ☆26Updated 9 months ago
- Code for ACL 2022 paper "Semi-Supervised Formality Style Transfer with Consistency Training".☆17Updated 3 years ago
- ☆36Updated 2 years ago
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)☆59Updated last year
- [ACL 2023] Code and Data Repo for Paper "Element-aware Summary and Summary Chain-of-Thought (SumCoT)"☆53Updated last year
- Official implementation of the ACL 2023 paper: "Zero-shot Faithful Factual Error Correction"☆17Updated last year
- This code accompanies the paper DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering.☆16Updated 2 years ago
- We construct and introduce DIALFACT, a testing benchmark dataset crowd-annotated conversational claims, paired with pieces of evidence fr…☆41Updated 2 years ago
- ☆16Updated 2 years ago
- [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models☆81Updated 9 months ago
- ☆11Updated last year
- Code for ACL 2023 paper "BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases".☆21Updated last year
- ☆13Updated 2 years ago
- Repository for ACL 2022 paper Mix and Match: Learning-free Controllable Text Generation using Energy Language Models☆44Updated 3 years ago
- BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages☆34Updated last month
- ☆48Updated 2 years ago
- Codes for ACL 2023 Paper "Fact-Checking Complex Claims with Program-Guided Reasoning"☆31Updated 2 years ago
- ☆44Updated last year
- Official Code for the papers: "Controlled Text Generation as Continuous Optimization with Multiple Constraints" and "Gradient-based Const…☆62Updated last year
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆65Updated last year
- ☆18Updated last year
- Code and data for the FACTOR paper☆47Updated last year
- The contrastive token loss function for reducing generative repetition of autoregressive neural language models.☆13Updated 3 years ago