conftrace_

model behavior

26 papers

Explore in graph

Co-occurring keywords

language model (4599) large language model (13587) influence function (143) model interpretability (519) deep neural network (1803) training data attribution (10) circuit analysis (17) mechanistic interpretability (133) human evaluation (379) bias detection (419)

Papers

Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals distinct Multi-Turn Behavior in LLMs ACL 2026
A Pipeline to Assess Merging Methods via Behavior and Internals EMNLP 2025
LLMs Don’t Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations EMNLP 2025
Decoding Emergent Big Five Traits in Large Language Models: Temperature-Dependent Expression and Architectural Clustering IJCNLP 2025
Extracting and Understanding the Superficial Knowledge in Alignment NAACL 2025
Do Influence Functions Work on Large Language Models? EMNLP 2025
Can Role Vectors Affect LLM Behaviour? EMNLP 2025
Enhancing Automated Interpretability with Output-Centric Feature Descriptions ACL 2025
Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions EMNLP 2025
How Persuasive Is Your Context? EMNLP 2025
Training Data Attribution via Approximate Unrolling NIPS 2024
Hypothesis Testing the Circuit Hypothesis in LLMs NIPS 2024
Unlearning Traces the Influential Training Data of Language Models ACL 2024
Information Flow Routes: Automatically Interpreting Language Models at Scale EMNLP 2024
Nichelle and Nancy: The Influence of Demographic Attributes and Tokenization Length on First Name Biases ACL 2023
Unnatural language processing: How do language models handle machine-generated prompts? EMNLP 2023
Are Language Models Worse than Humans at Following Prompts? It’s Complicated EMNLP 2023
Discovering Language Model Behaviors with Model-Written Evaluations ACL 2023
What Do You See in this Patient? Behavioral Testing of Clinical NLP Models NAACL 2022
Text Characterization Toolkit (TCT) IJCNLP 2022
i-Algebra: Towards Interactive Interpretability of Deep Neural Networks AAAI 2021
Connecting Attributions and QA Model Behavior on Realistic Counterfactuals EMNLP 2021
Human-Model Divergence in the Handling of Vagueness ACL 2021
Evaluating and Characterizing Human Rationales EMNLP 2020
Obtaining Faithful Interpretations from Compositional Neural Networks ACL 2020