Search Results for author:
Found 14 papers, 13 papers with code
Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension
We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs), which serves as a crucial step in building trust between humans and LLMs.
Contrastive Instruction Tuning
Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks.
On Prompt-Driven Safeguarding for Large Language Models
Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) from complying with queries that contain harmful intents.
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks
Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions.
Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning
Large language models (LLMs) have shown impressive performance in following natural language instructions to solve unseen tasks.
Efficient Shapley Values Estimation by Amortization for Text Classification
In practice, Shapley Values are often estimated with a small number of stochastic model evaluations.
Red Teaming Language Model Detectors with Language Models
The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users.
Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation
Instruction tuning has emerged to enhance the capabilities of large language models (LLMs) to comprehend instructions and generate appropriate responses.
CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning
Multimodal contrastive pretraining has been used to train multimodal representation models, such as CLIP, on large amounts of paired image-text data.
ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation
Finally, our analysis shows that the two types of uncertainty provided by \textbf{ADDMU} can be leveraged to characterize adversarial examples and identify the ones that contribute most to model's robustness in adversarial training.
On the Sensitivity and Stability of Model Interpretations in NLP
We propose two new criteria, sensitivity and stability, that provide complementary notions of faithfulness to the existed removal-based criteria.
On the Robustness of Language Encoders against Grammatical Errors
We conduct a thorough study to diagnose the behaviors of pre-trained language encoders (ELMo, BERT, and RoBERTa) when confronted with natural grammatical errors.
Entity-Relation Extraction as Multi-Turn Question Answering
In this paper, we propose a new paradigm for the task of entity-relation extraction.
Ranked #1 on
Relation Extraction
on ACE 2005
(Sentence Encoder metric)
Glyce: Glyph-vectors for Chinese Character Representations
However, due to the lack of rich pictographic evidence in glyphs and the weak generalization ability of standard computer vision models on character data, an effective way to utilize the glyph information remains to be found.
Ranked #1 on
Chinese Sentence Pair Classification
on LCQMC
Chinese Dependency Parsing
Chinese Named Entity Recognition
+21
