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.
84 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on natural language processing
84 notes, page 4 of 4
Semantic Early-Stopping for Iterative LLM Agent Loops
The research presents a method called semantic early-stopping for multi-agent large language model (LLM) loops, such as a Writer and a Critic. The goal is to halt the loop when the consecutive draft embeddings no…
Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text
The paper presents GAversary, a new method for generating adversarial attacks on natural language models using a Genetic Algorithm (GA). This method is able to reduce the accuracy of several target models significantly…
Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text
Researchers have developed a new method called GAversary, which uses a Genetic Algorithm (GA) and GloVe embeddings to generate adversarial attacks on natural language models. These attacks can significantly reduce the…
Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation
This research compares the effectiveness of encoder classifiers (using models like ModernBERT and Ettin) against LLM-based judges in identifying harmful outputs from large language models (LLMs). The study evaluates…
Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization
The authors present a framework for evaluating and comparing different types of RAG (Retrieval Augmented Generation) scenarios, including GraphRAG and Agentic RAG. They provide implementations for nine standardized RAG…
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Researchers present a new method called 'progress advantage' for evaluating Language Learning Models (LLMs) without the need for dedicated reward model training. This method is based on reinforcement learning (RL)…
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment
Researchers have proposed a framework called SARA (Semantically Anchored Routing Alignment) to improve the performance of multilingual language models in low-resource languages. The framework aligns the routing…
EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence
Researchers have developed a new benchmark called Evidence-Grounded Video Question Answering Benchmark (EG-VQA) to evaluate the performance of video question answering models. The benchmark is unique because it…
Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerce
The authors propose a new model for e-commerce where buyers use micro-payments to access detailed, verified information about products from sellers and reviewers. This model is designed for autonomous agent shoppers…
Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerce
The authors propose a new model for e-commerce where buyers pay small amounts of money to access detailed, verified information about products through the use of agent-native micro-payment rails. This model is designed…
Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts
The authors present TF-RefusalBench, a multilingual benchmark for assessing over-alignment in legal language models used by the Swiss Federal Supreme Court. They find that over-alignment is complex and influenced by…
UnBias-Plus: Detect, Explain, and Rewrite Bias
UnBias-Plus is a new open-source toolkit that aims to address the issue of bias in natural language content across various domains like journalism, education, and AI research. The toolkit offers four key features…
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.
