Picture for Chandan Singh

Chandan Singh

Shammie

Interpretable Language Modeling via Induction-head Ngram Models

Add code
Oct 31, 2024
Figure 1 for Interpretable Language Modeling via Induction-head Ngram Models
Figure 2 for Interpretable Language Modeling via Induction-head Ngram Models
Figure 3 for Interpretable Language Modeling via Induction-head Ngram Models
Figure 4 for Interpretable Language Modeling via Induction-head Ngram Models
Viaarxiv icon

Bayesian Concept Bottleneck Models with LLM Priors

Add code
Oct 21, 2024
Figure 1 for Bayesian Concept Bottleneck Models with LLM Priors
Figure 2 for Bayesian Concept Bottleneck Models with LLM Priors
Figure 3 for Bayesian Concept Bottleneck Models with LLM Priors
Figure 4 for Bayesian Concept Bottleneck Models with LLM Priors
Viaarxiv icon

Vector-ICL: In-context Learning with Continuous Vector Representations

Add code
Oct 08, 2024
Viaarxiv icon

A generative framework to bridge data-driven models and scientific theories in language neuroscience

Add code
Oct 01, 2024
Figure 1 for A generative framework to bridge data-driven models and scientific theories in language neuroscience
Figure 2 for A generative framework to bridge data-driven models and scientific theories in language neuroscience
Figure 3 for A generative framework to bridge data-driven models and scientific theories in language neuroscience
Figure 4 for A generative framework to bridge data-driven models and scientific theories in language neuroscience
Viaarxiv icon

Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering

Add code
Sep 16, 2024
Figure 1 for Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
Figure 2 for Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
Figure 3 for Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
Figure 4 for Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
Viaarxiv icon

Crafting Interpretable Embeddings by Asking LLMs Questions

Add code
May 26, 2024
Viaarxiv icon

Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries

Add code
Mar 01, 2024
Figure 1 for Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
Figure 2 for Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
Figure 3 for Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
Figure 4 for Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
Viaarxiv icon

Learning a Decision Tree Algorithm with Transformers

Add code
Feb 06, 2024
Viaarxiv icon

Rethinking Interpretability in the Era of Large Language Models

Add code
Jan 30, 2024
Figure 1 for Rethinking Interpretability in the Era of Large Language Models
Figure 2 for Rethinking Interpretability in the Era of Large Language Models
Viaarxiv icon

Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning

Add code
Jan 25, 2024
Viaarxiv icon