Papers by Insup Lee
TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) often generate incorrect responses based on made-up facts, which are called hallucinations. |
| Approach: | They propose a framework that combines Retrieval Augmented Generation with conformal prediction to provide the first end-to-end statistical correctness guarantee for RAG. |
| Outcome: | The proposed framework reduces prediction set size by 16.2% on average compared to an ablation. |
Uncertainty in Language Models: Assessment through Rank-Calibration (2024.emnlp-main)
Copied to clipboard
Xinmeng Huang, Shuo Li, Mengxin Yu, Matteo Sesia, Hamed Hassani, Insup Lee, Osbert Bastani, Edgar Dobriban
| Challenge: | Language Models (LMs) have shown promising performance in natural language generation . however, it is crucial to correctly quantify their level of uncertainty in responding to inputs. |
| Approach: | They propose a framework to quantify uncertainty and confidence for Large Language Models . they use a Rank-calibration framework to measure uncertainty and confident responses . |
| Outcome: | The proposed framework assesses uncertainty and confidence measures for LMs. |
MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. |
| Approach: | They propose a multilingual guardrail with reasoning for prompt classification that integrates culturally and linguistically nuanced variants and supervised fine-tuning. |
| Outcome: | The proposed guardrail outperforms baselines across in-domain and out-of-domain languages by more than 15%. |
In and Out-of-Domain Text Adversarial Robustness via Label Smoothing (2023.acl-short)
Copied to clipboard
| Challenge: | Existing studies show that state-of-the-art NLP models are vulnerable to adversarial attacks . label smoothing has been proven effective in a variety of applications and modalities . |
| Approach: | They propose to use label smoothing to improve adversarial robustness in pre-trained models against various popular attacks. |
| Outcome: | The proposed method significantly improves adversarial robustness in pre-trained models against various popular attacks. |
Bootstrapping Small & High Performance Language Models with Unmasking-Removal Training Policy (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models (LMs) have shown promising ability on handling various downstream tasks including textual classification and question answering. |
| Approach: | They propose to use BabyBERTa to train child-directed speech without unmasking words while masking parameters to improve grammatical accuracy. |
| Outcome: | The proposed model achieves grammatical ability comparable to RoBERTa-base model, which is trained on 6,000 times more words and 15 times more parameters. |