“‘Inner Monologue (AI)’ Tag”,2019-12-22 (knowledge distillation, instruct-tuning LLMs, AI emergence, meta-learning, RL scaling, forecasting; backlinks)⁠:

Bibliography for tag ai/nn/transformer/gpt/inner-monologue, most recent first: 6 related tags, 178 annotations, & 110 links (parent).

[page summary]

• See Also
• Gwern
  • “Free-Play Periods for RL Agents”, Gwern2023
  • “It Looks Like You’re Trying To Take Over The World”, Gwern2022
• Links
  • “Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models”, Ruis et al 2024
  • “Mind Your Step (by Step): Chain-Of-Thought Can Reduce Performance on Tasks Where Thinking Makes Humans Worse”, Liu et al 2024
  • “Thinking LLMs: General Instruction Following With Thought Generation”, Wu et al 2024
  • “When a Language Model Is Optimized for Reasoning, Does It Still Show Embers of Autoregression? An Analysis of OpenAI O1”, McCoy et al 2024
  • “Evaluation of OpenAI O1: Opportunities and Challenges of AGI”, Zhong et al 2024
  • “LLMs Still Can’t Plan; Can LRMs? A Preliminary Evaluation of OpenAI’s O1 on PlanBench”, Valmeekam et al 2024
  • “Training Language Models to Self-Correct via Reinforcement Learning”, Kumar et al 2024
  • “To CoT or Not to CoT? Chain-Of-Thought Helps Mainly on Math and Symbolic Reasoning”, Sprague et al 2024
  • “Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process”, Ye et al 2024
  • “Connecting the Dots: LLMs Can Infer and Verbalize Latent Structure from Disparate Training Data”, Treutlein et al 2024
  • “Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?”, Lee et al 2024
  • “OlympicArena: Benchmarking Multi-Discipline Cognitive Reasoning for Superintelligent AI”, Huang et al 2024
  • “How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad”, Abbe et al 2024
  • “OmegaPRM: Improve Mathematical Reasoning in Language Models by Automated Process Supervision”, Luo et al 2024
  • “MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark”, Wang et al 2024
  • “A Theoretical Understanding of Self-Correction through In-Context Alignment”, Wang et al 2024
  • “Intelligent Go-Explore (IGE): Standing on the Shoulders of Giant Foundation Models”, Lu et al 2024
  • “From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step”, Deng et al 2024
  • “Retrieval Head Mechanistically Explains Long-Context Factuality”, Wu et al 2024
  • “Let’s Think Dot by Dot: Hidden Computation in Transformer Language Models”, Pfau et al 2024
  • “Autonomous LLM-Driven Research from Data to Human-Verifiable Research Papers”, Ifargan et al 2024
  • “Missed Connections: Lateral Thinking Puzzles for Large Language Models”, Todd et al 2024
  • “ChatGPT Can Predict the Future When It Tells Stories Set in the Future About the Past”, Pham & Cunningham2024
  • “Visualization-Of-Thought Elicits Spatial Reasoning in Large Language Models”, Wu et al 2024
  • “Do Language Models Plan Ahead for Future Tokens?”, Wu et al 2024
  • “FABLES: Evaluating Faithfulness and Content Selection in Book-Length Summarization”, Kim et al 2024
  • “Re-Evaluating GPT-4’s Bar Exam Performance”, Martínez2024
  • “Long-Form Factuality in Large Language Models”, Wei et al 2024
  • “Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking”, Zelikman et al 2024
  • “RNNs Are Not Transformers (Yet): The Key Bottleneck on In-Context Retrieval”, Wen et al 2024
  • “Tokenization Counts: the Impact of Tokenization on Arithmetic in Frontier LLMs”, Singh & Strouse2024
  • “Chain-Of-Thought Empowers Transformers to Solve Inherently Serial Problems”, Li et al 2024
  • “Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models”, Levy et al 2024
  • “Why Are Sensitive Functions Hard for Transformers?”, Hahn & Rofin2024
  • “Chain-Of-Thought Reasoning Without Prompting”, Wang & Zhou2024
  • “V-STaR: Training Verifiers for Self-Taught Reasoners”, Hosseini et al 2024
  • “More Agents Is All You Need”, Li et al 2024
  • “The Impact of Reasoning Step Length on Large Language Models”, Jin et al 2024
  • “Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach”, Ma et al 2023
  • “Beyond Human Data: Scaling Self-Training for Problem-Solving With Language Models (ReST^EM)”, Singh et al 2023
  • “Tree of Attacks (TAP): Jailbreaking Black-Box LLMs Automatically”, Mehrotra et al 2023
  • “Universal Self-Consistency for Large Language Model Generation”, Chen et al 2023
  • “Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine”, Nori et al 2023
  • “Training Chain-Of-Thought via Latent-Variable Inference”, Phan et al 2023
  • “Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks”, Ramesh et al 2023
  • “On Measuring Faithfulness or Self-Consistency of Natural Language Explanations”, Parcalabescu & Frank2023
  • “Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations”, Hong et al 2023
  • “Large Language Models Can Strategically Deceive Their Users When Put Under Pressure”, Scheurer et al 2023
  • “Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves”, Deng et al 2023
  • “Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation”, Ding et al 2023
  • “Implicit Chain-Of-Thought Reasoning via Knowledge Distillation”, Deng et al 2023
  • “Preventing Language Models From Hiding Their Reasoning”, Roger & Greenblatt2023
  • “Branch-Solve-Merge Improves Large Language Model Evaluation and Generation”, Saha et al 2023
  • “Can GPT Models Be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on Mock CFA Exams”, Callanan et al 2023
  • “The Expressive Power of Transformers With Chain-Of-Thought”, Merrill & Sabharwal2023
  • “Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models”, Zhou et al 2023
  • “Large Language Models Cannot Self-Correct Reasoning Yet”, Huang et al 2023
  • “Think Before You Speak: Training Language Models With Pause Tokens”, Goyal et al 2023
  • “Embers of Autoregression: Understanding Large Language Models Through the Problem They Are Trained to Solve”, McCoy et al 2023
  • “Contrastive Decoding Improves Reasoning in Large Language Models”, O’Brien & Lewis2023
  • “Re-Reading Improves Reasoning in Large Language Models”, Xu et al 2023
  • “From Sparse to Dense: GPT-4 Summarization With Chain of Density (CoD) Prompting”, Adams et al 2023
  • “Graph of Thoughts: Solving Elaborate Problems With Large Language Models”, Besta et al 2023
  • “Solving Challenging Math Word Problems Using GPT-4 Code Interpreter With Code-Based Self-Verification”, Zhou et al 2023
  • “Android in the Wild: A Large-Scale Dataset for Android Device Control”, Rawles et al 2023
  • “LLMs As Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines With LLMs”, Wu et al 2023
  • “TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT”, Zha et al 2023
  • “Question Decomposition Improves the Faithfulness of Model-Generated Reasoning”, Radhakrishnan et al 2023
  • “Measuring Faithfulness in Chain-Of-Thought Reasoning”, Lanham et al 2023
  • “Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration”, Wang et al 2023
  • “Explaining Competitive-Level Programming Solutions Using LLMs”, Li et al 2023
  • “Teaching Arithmetic to Small Transformers”, Lee et al 2023
  • “Language Models Are Weak Learners”, Manikandan et al 2023
  • “Let’s Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning”, Ma et al 2023
  • “GKD: Generalized Knowledge Distillation for Auto-Regressive Sequence Models”, Agarwal et al 2023
  • “Large Language Models As Tax Attorneys: A Case Study in Legal Capabilities Emergence”, Nay et al 2023
  • “Iterative Translation Refinement With Large Language Models”, Chen et al 2023
  • “Thought Cloning: Learning to Think While Acting by Imitating Human Thinking”, Hu & Clune2023
  • “Let’s Verify Step by Step”, Lightman et al 2023
  • “Towards Revealing the Mystery behind Chain-Of-Thought: A Theoretical Perspective”, Feng et al 2023
  • “Improving Factuality and Reasoning in Language Models through Multiagent Debate”, Du et al 2023
  • “How Language Model Hallucinations Can Snowball”, Zhang et al 2023
  • “Tree of Thoughts (ToT): Deliberate Problem Solving With Large Language Models”, Yao et al 2023
  • “Large Language Model Programs”, Schlag et al 2023
  • “Language Models Don’t Always Say What They Think: Unfaithful Explanations in Chain-Of-Thought Prompting”, Turpin et al 2023
  • “Distilling Step-By-Step! Outperforming Larger Language Models With Less Training Data and Smaller Model Sizes”, Hsieh et al 2023
  • “Decomposition Enhances Reasoning via Self-Evaluation Guided Decoding”, Xie et al 2023
  • “LLM+P: Empowering Large Language Models With Optimal Planning Proficiency”, Liu et al 2023
  • “Boosting Theory-Of-Mind Performance in Large Language Models via Prompting”, Moghaddam & Honey2023
  • “Think Before You Act: Unified Policy for Interleaving Language Reasoning With Actions”, Mezghani et al 2023
  • “Language Models Can Solve Computer Tasks”, Kim et al 2023
  • “Reflexion: Language Agents With Verbal Reinforcement Learning”, Shinn et al 2023
  • “How Well Do Large Language Models Perform in Arithmetic Tasks?”, Yuan et al 2023
  • “SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models”, Manakul et al 2023
  • “Language Is Not All You Need: Aligning Perception With Language Models (Kosmos-1)”, Huang et al 2023
  • “Multimodal Chain-Of-Thought Reasoning in Language Models”, Zhang et al 2023
  • “Faithful Chain-Of-Thought Reasoning”, Lyu et al 2023
  • “Large Language Models Are Versatile Decomposers: Decompose Evidence and Questions for Table-Based Reasoning”, Ye et al 2023
  • “ChatGPT Goes to Law School”, Choi et al 2023
  • “Large Language Models As Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards”, Nay2023
  • “Interactive-Chain-Prompting (INTERCPT): Ambiguity Resolution for Crosslingual Conditional Generation With Interaction”, Pilault et al 2023
  • “Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes”, Reppert et al 2023
  • “Solving Math Word Problems With Process & Outcome-Based Feedback”, Uesato et al 2022
  • “PAL: Program-Aided Language Models”, Gao et al 2022
  • “Measuring Progress on Scalable Oversight for Large Language Models”, Bowman et al 2022
  • “U-PaLM: Transcending Scaling Laws With 0.1% Extra Compute”, Tay et al 2022
  • “Large Language Models Can Self-Improve”, Huang et al 2022
  • “Challenging BIG-Bench Tasks (BBH) and Whether Chain-Of-Thought Can Solve Them”, Suzgun et al 2022
  • “Self-Ask: Measuring and Narrowing the Compositionality Gap in Language Models (Bamboogle)”, Press et al 2022
  • “Language Models Are Multilingual Chain-Of-Thought Reasoners”, Shi et al 2022
  • “ReAct: Synergizing Reasoning and Acting in Language Models”, Yao et al 2022
  • “Dynamic Prompt Learning via Policy Gradient for Semi-Structured Mathematical Reasoning”, Lu et al 2022
  • “FOLIO: Natural Language Reasoning With First-Order Logic”, Han et al 2022
  • “Faithful Reasoning Using Large Language Models”, Creswell & Shanahan2022
  • “Limitations of Language Models in Arithmetic and Symbolic Induction”, Qian et al 2022
  • “Language Models Can Teach Themselves to Program Better”, Haluptzok et al 2022
  • “Language Model Cascades”, Dohan et al 2022
  • “CodeT: Code Generation With Generated Tests”, Chen et al 2022
  • “Can Large Language Models Reason about Medical Questions?”, Liévin et al 2022
  • “Inner Monologue: Embodied Reasoning through Planning With Language Models”, Huang et al 2022
  • “Exploring Length Generalization in Large Language Models”, Anil et al 2022
  • “Language Models (Mostly) Know What They Know”, Kadavath et al 2022
  • “Solving Quantitative Reasoning Problems With Language Models”, Lewkowycz et al 2022
  • “Maieutic Prompting: Logically Consistent Reasoning With Recursive Explanations”, Jung et al 2022
  • “Large Language Models Are Zero-Shot Reasoners”, Kojima et al 2022
  • “Instruction Induction: From Few Examples to Natural Language Task Descriptions”, Honovich et al 2022
  • “Least-To-Most Prompting Enables Complex Reasoning in Large Language Models”, Zhou et al 2022
  • “Dialog Inpainting: Turning Documents into Dialogues”, Dai et al 2022
  • “Unifying Language Learning Paradigms”, Tay et al 2022
  • “Can Language Models Learn from Explanations in Context?”, Lampinen et al 2022
  • “Socratic Models: Composing Zero-Shot Multimodal Reasoning With Language”, Zeng et al 2022
  • “STaR: Bootstrapping Reasoning With Reasoning”, Zelikman et al 2022
  • “A Conversational Paradigm for Program Synthesis”, Nijkamp et al 2022
  • “Self-Consistency Improves Chain-Of-Thought Reasoning in Language Models”, Wang et al 2022
  • “Learning-By-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension”, Zhao et al 2022
  • “PromptChainer: Chaining Large Language Model Prompts through Visual Programming”, Wu et al 2022
  • “Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models”, Wei et al 2022
  • “Reasoning Like Program Executors”, Pi et al 2022
  • “A Neural Network Solves and Generates Mathematics Problems by Program Synthesis: Calculus, Differential Equations, Linear Algebra, and More”, Drori et al 2021
  • “DREAM: Uncovering Mental Models behind Language Models”, Gu et al 2021
  • “Reframing Human-AI Collaboration for Generating Free-Text Explanations”, Wiegreffe et al 2021
  • “NeuroLogic A^✱esque Decoding: Constrained Text Generation With Lookahead Heuristics”, Lu et al 2021
  • “WebGPT: Improving the Factual Accuracy of Language Models through Web Browsing”, Hilton et al 2021
  • “Few-Shot Self-Rationalization With Natural Language Prompts”, Marasović et al 2021
  • “Training Verifiers to Solve Math Word Problems”, Cobbe et al 2021
  • “Unsupervised Neural Machine Translation With Generative Language Models Only”, Han et al 2021
  • “Show Your Work: Scratchpads for Intermediate Computation With Language Models”, Nye et al 2021
  • “AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts”, Wu et al 2021
  • “Teaching Autoregressive Language Models Complex Tasks By Demonstration”, Recchia2021
  • “Program Synthesis With Large Language Models”, Austin et al 2021
  • “Decision Transformer: Reinforcement Learning via Sequence Modeling”, Chen et al 2021
  • “Explainable Multi-Hop Verbal Reasoning Through Internal Monologue”, Liang et al 2021
  • “A Simple Method to Keep GPT-3 Focused in a Conversation”, Mayne2021
  • “Measuring Mathematical Problem Solving With the MATH Dataset”, Hendrycks et al 2021
  • “Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm”, Reynolds & McDonell2021
  • “How We Accidentally Gave Our Bots Their Personalities”, Latitude2021
  • “Word in Context: Agent and Agent Clarification (69% Dev)”, Brockman2020
  • “I Found That Getting GPT-3 to Add Its Own “Internal Monologue” in Parentheses to Be a Helpful Strategy…”, blixt 2020
  • kleptid @ “2020-07-17”
  • kleptid @ “2020-07-17”
  • “Inducing Self-Explanation: a Meta-Analysis”, Bisra et al 2018
  • “Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems”, Ling et al 2017
  • “Why Do Humans Reason? Arguments for an Argumentative Theory”, Mercier & Sperber2011
  • “How to Dramatically Improve the Reasoning Ability of GPT-3”
  • “A Preliminary Exploration into Factored Cognition With Language Models”
  • “WiC_SelfContextStuffingImproved_Last10_stuft_examplesNV.ipynb”
  • “Vincent-163/transformer-Arithmetic”
  • “Magic ToDo List Creator”
  • “Short Story on AI: ‘Forward Pass’”, Karpathy2024
  • “AI Dungeon Players Can Now Translate Their Stories into Emojis by Just Clicking a Button.”
  • “Solving Math Word Problems: We’ve Trained a System That Solves Grade School Math Problems With Nearly Twice the Accuracy of a Fine-Tuned GPT-3 Model. It Solves about 90% As Many Problems As Real Kids: a Small Sample of 9-12 Year Olds Scored 60% on a Test from Our Dataset, While Our System Scored 55% on Those Same Problems. This Is Important Because Today’s AI Is Still Quite Weak at Commonsense Multistep Reasoning, Which Is Easy Even for Grade School Kids. We Achieved These Results by Training Our Model to Recognize Its Mistakes, so That It Can Try Repeatedly Until It Finds a Solution That Works”
  • “Prompting Diverse Ideas: Increasing AI Idea Variance”
  • “Teaching a Neural Network to Use a Calculator”
  • “Connecting the Dots: LLMs Can Infer & Verbalize Latent Structure from Training Data”
  • “Preventing Language Models from Hiding Their Reasoning”
  • “Steganography in Chain-Of-Thought Reasoning”
  • “Visible Thoughts Project and Bounty Announcement”
  • bucketofkets
  • Sort By Magic
    • llm-research
    • self-evaluation
    • chain-of-thought
  • Wikipedia
• Miscellaneous
• Bibliography

Backlinks: