NLP Wiki

User Tools

Site Tools

Trace: • hyperparameter_tuning • curriculum_learning • distributed_training • log_linear_models • software
nlp:explainability

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
nlp:explainability [2025/03/26 23:46] – [Interpretability and Explainability In LLMs] jmflanignlp:explainability [2025/06/01 23:17] (current) – [Related Pages] jmflanig
Line 7: Line 7:
   * [[https://arxiv.org/pdf/2012.14261.pdf|Zhang et al 2020 - A Survey on Neural Network Interpretability]]   * [[https://arxiv.org/pdf/2012.14261.pdf|Zhang et al 2020 - A Survey on Neural Network Interpretability]]
   * [[https://arxiv.org/pdf/2010.00389.pdf|Thayaparan et al 2020 - A Survey on Explainability in Machine Reading Comprehension]]   * [[https://arxiv.org/pdf/2010.00389.pdf|Thayaparan et al 2020 - A Survey on Explainability in Machine Reading Comprehension]]
 +  * [[https://arxiv.org/pdf/2207.13243|Rauker et al 2022 - Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks]]
  
 ==== Papers ==== ==== Papers ====
Line 32: Line 33:
  
 ===== Interpretability and Explainability In LLMs ===== ===== Interpretability and Explainability In LLMs =====
-  * [[https://openaipublic.blob.core.windows.net/neuron-explainer/paper/index.html|Bills et al 2023 - Language models can explain neurons in language models]] +  * **Overviews** 
-  * [[https://arxiv.org/pdf/2402.10688|Zhao et al 2024 - Towards Uncovering How Large Language Model Works: An Explainability Perspective]]** Good review paper +    * [[https://arxiv.org/pdf/2401.12874|Luo & Specia 2024 - From Understanding to Utilization: A Survey on Explainability for Large Language Models]] 
 +    * [[https://arxiv.org/pdf/2402.10688|Zhao et al 2024 - Towards Uncovering How Large Language Model Works: An Explainability Perspective]] This is an ok paper, but it cites almost none of the work before 2021 or work outside of the mechanistic interpretability literature. 
 +  * **Resources** 
 +    * [[https://burnycoder.github.io/Landing/Contents/Exobrain/Topics/Mechanistic%20interpretability/|Paper list]] 
 +  * **Papers** 
 +    * [[https://openaipublic.blob.core.windows.net/neuron-explainer/paper/index.html|Bills et al 2023 - Language models can explain neurons in language models]] 
 +    * [[https://arxiv.org/pdf/2305.08809|Wu et al 2023 - Interpretability at Scale: Identifying Causal Mechanisms in Alpaca]] 
 +    * [[https://arxiv.org/pdf/2305.19911|Foote et al 2023 - Neuron to Graph: Interpreting Language Model Neurons at Scale]]
  
 ===== Natural Language Explanations ===== ===== Natural Language Explanations =====
Line 56: Line 63:
   * [[ml:Neural Network Psychology]]   * [[ml:Neural Network Psychology]]
   * [[Probing Experiments]]   * [[Probing Experiments]]
-  * [[Reasoning Chains]]+  * [[Reasoning#Reasoning Chains|Reasoning - Reasoning Chains]]
   * [[ml:Trustworthy AI]]   * [[ml:Trustworthy AI]]
   * [[ml:Visualizing Neural Networks]]   * [[ml:Visualizing Neural Networks]]
nlp/explainability.1743032780.txt.gz · Last modified: 2025/03/26 23:46 by jmflanig
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki