Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment

arXiv:2608.30842 · cs.CL · Submitted 2026-08-31 · Read on arXiv

cs.CL

Submitted: 2026-08-31

Updated: 2026-08-31

Code: https://github.com/google-research/vet

Terminology

• Verifier — 17× in this paper · explained in 2 episodes
• Alignment — 14× in this paper · explained in 1 episode
• Accuracy — 8× in this paper · explained in 1 episode
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• AI Alignment — 5× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Agentic Workflows — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Linguistic Annotation Workshop — 2× in this paper
• Test-time Scaling — 2× in this paper · explained in 2 episodes
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Best-of-N Sampling — 1× in this paper · explained in 2 episodes
• Calculate Confidence Interval — 1× in this paper
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Intersectionality — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Variance Estimation Toolkit — 1× in this paper

Sources

• Constitutional AI: Harmlessness from AI Feedback
• Whose Opinions Matter? Perspective-aware Models to Identify Opinions of Hate Speech Victims in Abusive Language Detection
• Training Verifiers to Solve Math Word Problems
• RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning
• D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation
• s1: Simple test-time scaling
• Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models
• Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement
• Self-critiquing models for assisting human evaluators
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• Reward Is Enough: LLMs Are In-Context Reinforcement Learners
• A Roadmap to Pluralistic Alignment
• Large Language Models as Optimizers
• TextGrad: Automatic "Differentiation" via Text
• Unlocking Recursive Thinking of LLMs: Alignment via Refinement
• Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
• EvoAgentX: An Automated Framework for Evolving Agentic Workflows
• Large Language Models Are Human-Level Prompt Engineers

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering