Field notes
2,343 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.
Click the web, then scroll to zoom
Every note is in the list below. The web of topics draws here once the page has loaded.
11 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on interpretability
11 notes
Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs
Across 18 base-instruct model pairs spanning Qwen, Llama, and Gemma, the authors report that harmfulness is more readily decoded from attention updates while MLP updates contribute more strongly to harm-selective…
External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing
The preprint presents a hidden-state method for identifying the onset and continuation of hallucinated spans rather than making only token-level binary judgments. It proposes an external observer model that probes the…
Multimodal Model Diffing for Feature Discovery and Control
Researchers developed a framework called MMDiff to help understand, control, and audit the behavior of Multimodal Large Language Models (MLLMs). The framework identifies features that are altered by multimodal…
LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings
Researchers introduce LEX-EC, a framework for analyzing the interpretability of large language models in assigning personality labels from text. The framework identifies and separates marginal distribution effects from…
M$^3$-Gen: Interpretable Multimodal Generation of Gene Expression Profiles Using Clinical and Imaging Data
M$^3$-Gen is a new framework that generates synthetic gene expression profiles using both clinical metadata and histopathology images. The method leverages a Generative Adversarial Network to create biologically…
AIMO Interpretability Challenge
The AIMO Interpretability Challenge is a competition proposed by researchers aimed at distinguishing robust from spurious reasoning in advanced mathematical language models. The challenge focuses on evaluating the…
X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models
The authors propose a new approach to make Electronic Health Records Foundation Models (FEMRs) more transparent by identifying the most influential tokens in the model's predictions. This is done using a…
TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models
Researchers propose a multi-agent system (MAS) called TreeAgent to automate bias labeling in forestry via expert decision trees and Vision-Language Models (VLMs). The MAS aims to reduce the need for human annotation…
TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models
Researchers propose a system called TreeAgent that uses artificial intelligence (AI) to classify tree heights in forestry remote sensing. The system combines decision trees created by experts with Vision-Language…
Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement
Researchers have developed a new system called BINEVAL for evaluating large language models (LLMs). This system breaks down the evaluation criteria into binary questions, making it easier to understand the results and…
Expresso-AI: Explainable Video-Based Deep Learning Models for Depression Diagnosis
The researchers have developed a new method for diagnosing depression using deep learning models and facial videos. Their approach provides interpretable explanations for the model's decisions, which can help health…
An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.
