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 2 of 4
Co-Evolving LLM Evaluators and Policies via DynamicRubric
The paper introduces DynamicRubric, a framework that co-evolves language model evaluators and policies by generating weighted binary rubrics for each candidate set and aggregating the resulting judgments into…
Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomy
The paper proposes a taxonomy to better understand curriculum learning (CL) in Natural Language Processing (NLP). The taxonomy aims to provide a systematic analysis of CL strategies by separating difficulty evaluation…
Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA
The paper presents a diagnostic framework called FiT (Find before Fine-Tune) to evaluate the suitability of small language models for cybersecurity question-answering tasks. The study finds that fine-tuning these…
Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
The authors propose a method to improve the accuracy of automatic speech recognition (ASR) models by controlling the activation of 'verbatim' versus 'intended' transcription styles. They argue that current models…
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
Researchers propose a new method called SOPHIA for controlling the reasoning process of large language models, which are currently uncontrollable despite their extended use. The proposed method involves treating each…
HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization
The paper proposes a new method called Highlight-guided Attention Steering (HAS) for video summarization using Multimodal Large Language Models (M-LLMs). HAS aims to enhance the understanding of videos by focusing…
MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models
The paper introduces MADA-RL, a method for fine-tuning compact language models with limited budgets. It specializes the models into generator and critic roles and trains them using a debate-aware learning signal. The…
SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs
Researchers present SelectInfer, a neuron-level optimization framework for Large Language Models (LLMs) that can run efficiently on resource-constrained edge devices. It reduces memory footprint and computation by…
Stress Testing Concept Erasure with Large Language Model Agents
The paper introduces a new framework called Stress Testing Agents for Concept Erasure (STACE). STACE uses multiple Large Language Model (LLM) agents to stress-test models that have had certain concepts erased from…
AutoSynthesis: An agentic system for automated meta-analysis
AutoSynthesis is a multi-agent system designed for automated meta-analysis of research questions in natural language. The system searches for scientific literature, assesses eligibility, extracts quantitative…
Long-Context Fine-Tuning with Limited VRAM
Researchers introduce Hierarchical Global Attention (HGA) to reduce memory usage during long training sequences in large language models. They use segment-wise backpropagation, tiered KV storage, and detach older data…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers have introduced a new benchmark called MM-IssueLoc for evaluating the effectiveness of systems in repository-level issue localization that also includes visual evidence such as screenshots, error dialogs…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
The paper introduces MM-IssueLoc, a benchmark and evaluation protocol for repository-level issue localization that includes visual evidence. The benchmark has 652 issue-PR instances across 23 languages with annotations…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
The paper introduces MM-IssueLoc, a new benchmark and evaluation protocol for repository-level issue localization with visual evidence. The benchmark contains over 650 issue-PR instances across multiple languages…
SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
The text introduces SciDiagramEdit, a framework for automating the editing of scientific diagrams in research papers based on natural language instructions. The framework learns from natural paper revisions and…
SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
The authors introduce SciDiagramEdit, a system designed to automate the time-consuming process of editing scientific diagrams in research papers based on natural language instructions. The system learns from paper…
Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution
Researchers propose a graph neural network approach to detect and analyze reasoning structures in large language models (LLMs) generated texts for improved robustness against paraphrasing and obfuscation techniques…
teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data
Researchers have developed teLLMe, a system to analyze urban driving data for understanding traffic safety and congestion by answering causal questions. The system uses dashcam annotations to build a structured event…
Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs
Researchers propose a new method called Grounded Context Preference Optimization (Groc-PO) to improve the truthfulness and utility of Multimodal Large Language Models (MLLMs). Current MLLMs often make errors due to…
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
Researchers present Pythia, a multi-agent system that automatically generates and optimizes extraction prompts for clinical concepts without manual engineering or fine-tuning. They compare Pythia with a curated lexicon…
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
A new system called Pythia was developed, which automatically generates and optimizes extraction prompts for clinical concepts without the need for manual prompt engineering or fine-tuning. The researchers compared…
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
Researchers train a discrete diffusion language model to transcribe speech instead of using autoregressive decoders that emit one token at a time. The model is based on a mixture-of-experts called DiffusionGemma, and…
Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs
The authors present a method for creating counterfactual report mediators, which help align language models by making their reports invariant to certain influences (like pressure or prestige) and responsive to others…
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
The authors present a method for creating and refining evaluation metrics for self-improving language models (LLMs). The proposed method, called Double Ratchet, evolves metrics by combining small drawback detectors in…
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.
