Chandan Singh
- Papers
- 13
Cite
Notes
Only stored in your browser.
Authored papers
13Text Generation Beyond Discrete Token Sampling
arXiv 2025
OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Modalities
arXiv 2025
Vector-ICL: In-context Learning with Continuous Vector Representations
arXiv 2024
Rethinking Interpretability in the Era of Large Language Models
arXiv 2024
Learning a Decision Tree Algorithm with Transformers
arXiv 2024
Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
arXiv 2024
Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
arXiv 2024
Explaining black box text modules in natural language with language models
arXiv 2023
Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
arXiv 2023
Tree Prompting: Efficient Task Adaptation without Fine-Tuning
arXiv 2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
arXiv 2021
Interpretations are useful: penalizing explanations to align neural networks with prior knowledge
interpretations-are-useful-penalizing-1
Affiliations
Frequent co-authors
10from 13 papers