Article
What We Learned About LLM/VLMs in Healthcare AI Evaluation:
By
ā¢
ā¢
10Nils Feldhus
nfel
AI & ML interests
Interpretability, Explainability, Natural Language Generation
Recent Activity
upvoted
an
article
29 days ago
What We Learned About LLM/VLMs in Healthcare AI Evaluation:
liked
a Space
about 2 months ago
openlifescienceai/open_medical_llm_leaderboard
Organizations
nfel's activity
upvoted
an
article
29 days ago
liked
a
Space
about 2 months ago
authored
3
papers
5 months ago
Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools
Paper
ā¢
2108.13961
ā¢
Published
Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods
Paper
ā¢
2210.07222
ā¢
Published
InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations
Paper
ā¢
2310.05592
ā¢
Published
upvoted
a
paper
7 months ago
liked
2
models
7 months ago
liked
a
Space
8 months ago
liked
2
Spaces
9 months ago
reacted to
gsarti's
post with š
10 months ago
Post
š Today's pick in Interpretability & Analysis of LMs: SyntaxShap: Syntax-aware Explainability Method for Text Generation by
@kamara000
, R. Sevastjanova and M. El-Assady
Most model-agnostic post-hoc interpretability methods used nowadays in NLP were originally ported from tabular/CV domains with next to no adjustments to the intrinsic properties of textual inputs.
In this work, authors propose SyntaxSHAP, an adaptation of the Shapely value approach in which coalitions used to compute marginal contributions to importance scores are constrained by the syntax of the explained sentence. The resulting tree-based coalitions do not satisfy the efficiency assumption of Shapley values but preserves the symmetry, nullity and additivity axioms.
SyntaxSHAP is compared to other model-agnostic approaches on small (GPT-2 117M) and large (Mistral 7B) LMs, showing it produces explanations that are more faithful to model predictions and more semantically meaningful than other common methods, while also being more efficient than the base SHAP method.
š Paper: SyntaxShap: Syntax-aware Explainability Method for Text Generation (2402.09259)
š» Code: https://github.com/k-amara/syntax-shap
š All daily picks in LM interpretability: gsarti/daily-picks-in-interpretability-and-analysis-of-lms-65ae3339949c5675d25de2f9
Most model-agnostic post-hoc interpretability methods used nowadays in NLP were originally ported from tabular/CV domains with next to no adjustments to the intrinsic properties of textual inputs.
In this work, authors propose SyntaxSHAP, an adaptation of the Shapely value approach in which coalitions used to compute marginal contributions to importance scores are constrained by the syntax of the explained sentence. The resulting tree-based coalitions do not satisfy the efficiency assumption of Shapley values but preserves the symmetry, nullity and additivity axioms.
SyntaxSHAP is compared to other model-agnostic approaches on small (GPT-2 117M) and large (Mistral 7B) LMs, showing it produces explanations that are more faithful to model predictions and more semantically meaningful than other common methods, while also being more efficient than the base SHAP method.
š Paper: SyntaxShap: Syntax-aware Explainability Method for Text Generation (2402.09259)
š» Code: https://github.com/k-amara/syntax-shap
š All daily picks in LM interpretability: gsarti/daily-picks-in-interpretability-and-analysis-of-lms-65ae3339949c5675d25de2f9
liked
2
models
11 months ago
reacted to
gsarti's
post with š
11 months ago
Post
š Today's pick in Interpretability & Analysis of LMs: LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools by
@qiaw99
@tanikina
@nfel
et al.
Authors introduce LLMCheckup, a conversational interface connecting an LLM to several interpretability tools (feature attribution methods, similarity, counterfactual/rationale generation) allowing users to inquire about LLM predictions using natural language. The interface consolidates several interpretability methods in a unified chat interface, simplifying future investigations into natural language explanations.
š Paper: LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools (2401.12576)
š» Code: https://github.com/DFKI-NLP/LLMCheckup
š„ Demo video: https://www.youtube.com/watch?v=ZwN8ZQSXoOU
Authors introduce LLMCheckup, a conversational interface connecting an LLM to several interpretability tools (feature attribution methods, similarity, counterfactual/rationale generation) allowing users to inquire about LLM predictions using natural language. The interface consolidates several interpretability methods in a unified chat interface, simplifying future investigations into natural language explanations.
š Paper: LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools (2401.12576)
š» Code: https://github.com/DFKI-NLP/LLMCheckup
š„ Demo video: https://www.youtube.com/watch?v=ZwN8ZQSXoOU
liked
a
model
11 months ago
upvoted
a
collection
11 months ago
liked
3
models
about 1 year ago
