Bibliography:

  1. ‘neural net’ tag

  2. ‘instruct-tuning LLMs’ tag

  3. ‘AlphaGo’ tag

  4. Research Ideas

  5. GPT-3 Creative Fiction

  6. Choose-Your-Own-Adventure AI Dungeon Games

  7. RNN Metadata for Mimicking Author Style

  8. Do LLMs estimate uncertainty well in instruction-following?

  9. SimpleStrat: Diversifying Language Model Generation with Stratification

  10. Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

  11. Be like a Goldfish, Don’t Memorize! Mitigating Memorization in Generative LLMs

  12. Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass

  13. Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo

  14. σ-GPTs: A New Approach to Autoregressive Models

  15. LLM Evaluators Recognize and Favor Their Own Generations

  16. Re-evaluating GPT-4’s bar exam performance

  17. Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

  18. Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews

  19. Chain-of-Thought Reasoning Without Prompting

  20. The Non-Effect of Sampling Temperature on Problem Solving in GPT-3.5/GPT-4

  21. Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM

  22. GIVT: Generative Infinite-Vocabulary Transformers

  23. Universal Self-Consistency for Large Language Model Generation

  24. Controlled Text Generation via Language Model Arithmetic

  25. Language Model Inversion

  26. SEDD: Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution

  27. Let Models Speak Ciphers: Multiagent Debate through Embeddings

  28. Contrastive Decoding Improves Reasoning in Large Language Models

  29. Accelerating LLM Inference with Staged Speculative Decoding

  30. Efficient Guided Generation for Large Language Models

  31. Copy Is All You Need

  32. Stay on topic with Classifier-Free Guidance

  33. Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs

  34. How Language Model Hallucinations Can Snowball

  35. Tractable Control for Autoregressive Language Generation

  36. MUX-PLMs: Pre-training Language Models with Data Multiplexing

  37. Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented Large Language Models

  38. DataMUX: Data Multiplexing for Neural Networks

  39. Witscript 3: A Hybrid AI System for Improvising Jokes in a Conversation

  40. A survey on text generation using generative adversarial networks

  41. Fast Inference from Transformers via Speculative Decoding

  42. The CRINGE Loss: Learning what language not to model

  43. Contrastive Decoding: Open-ended Text Generation as Optimization

  44. Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing (CoPoet)

  45. Contrastive Search Is What You Need For Neural Text Generation

  46. Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models

  47. Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio

  48. Ask Me Anything (AMA): A simple strategy for prompting language models

  49. Out of One, Many: Using Language Models to Simulate Human Samples

  50. Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

  51. Effidit: Your AI Writing Assistant

  52. DIRECTOR: Generator-Classifiers For Supervised Language Modeling

  53. RankGen: Improving Text Generation with Large Ranking Models

  54. Time Control: Language modeling via stochastic processes

  55. Controllable Natural Language Generation with Contrastive Prefixes

  56. Using natural language prompts for machine translation

  57. A Contrastive Framework for Neural Text Generation

  58. Typical Decoding for Natural Language Generation

  59. FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control

  60. A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models

  61. FRUIT: Faithfully Reflecting Updated Information in Text

  62. NeuroLogic Aesque Decoding: Constrained Text Generation with Lookahead Heuristics

  63. Relating Neural Text Degeneration to Exposure Bias

  64. Program Synthesis with Large Language Models

  65. Scarecrow: A Framework for Scrutinizing Machine Text

  66. Time-Aware Language Models as Temporal Knowledge Bases

  67. Machine Translation Decoding beyond Beam Search

  68. Controllable Generation from Pre-trained Language Models via Inverse Prompting

  69. Improving Diversity of Neural Text Generation via Inverse Probability Weighting

  70. There Once Was a Really Bad Poet, It Was Automated but You Didn’t Know It

  71. A Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks

  72. MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers

  73. Prefix-Tuning: Optimizing Continuous Prompts for Generation

  74. Bot-Adversarial Dialogue for Safe Conversational Agents

  75. Collaborative Storytelling with Large-scale Neural Language Models

  76. NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints

  77. Interacting with GPT-2 to Generate Controlled and Believable Musical Sequences in ABC Notation

  78. Training independent subnetworks for robust prediction

  79. MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models

  80. Weird AI Yankovic: Generating Parody Lyrics

  81. A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation

  82. GeDi: Generative Discriminator Guided Sequence Generation

  83. Mirostat: A Neural Text Decoding Algorithm that Directly Controls Perplexity

  84. Progressive Generation of Long Text

  85. This Word Does Not Exist

  86. true_poetry: Poetry generator by GPT-2 with meter and rhyme constraints

  87. Blender: A state-of-the-art open source chatbot

  88. Trading Off Diversity and Quality in Natural Language Generation

  89. Rapformer: Conditional Rap Lyrics Generation with Denoising Autoencoders

  90. A Hundred Visions and Revisions

  91. Top-K Training of GANs: Improving GAN Performance by Throwing Away Bad Samples

  92. Towards a Human-like Open-Domain Chatbot

  93. Controlling Text Generation with Plug and Play Language Models

  94. Plug and Play Language Models: A Simple Approach to Controlled Text Generation

  95. CTRL: A Conditional Transformer Language Model For Controllable Generation

  96. Neural Text Generation with Unlikelihood Training

  97. GROVER: Defending Against Neural Fake News

  98. The Curious Case of Neural Text Degeneration

  99. Good News, Everyone! Context driven entity-aware captioning for news images

  100. GPT-2 Neural Network Poetry

  101. Insertion Transformer: Flexible Sequence Generation via Insertion Operations

  102. Blockwise Parallel Decoding for Deep Autoregressive Models

  103. Language GANs Falling Short

  104. Discriminator Rejection Sampling

  105. OCD: Optimal Completion Distillation for Sequence Learning

  106. Controlling Linguistic Style Aspects in Neural Language Generation

  107. Six Challenges for Neural Machine Translation

  108. Language Generation with Recurrent Generative Adversarial Networks without Pre-training

  109. A Deep Reinforced Model for Abstractive Summarization

  110. Learning to Generate Reviews and Discovering Sentiment

  111. Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets

  112. Tuning Recurrent Neural Networks with Reinforcement Learning

  113. Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

  114. WaveNet: A Generative Model for Raw Audio

  115. Sequence Level Training with Recurrent Neural Networks

  116. Generative Concatenative Nets Jointly Learn to Write and Classify Reviews

  117. Semi-supervised Sequence Learning

  118. Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

  119. Controlling GPT-3 With Logit Bias

  120. 091471e73f0fc19d2c9594c40e3e3ea76baec149.html

  121. Feature: Beam Search for Improving Global Quality of New Text Samples

  122. Exclude Top Choices (XTC): A Sampler That Boosts Creativity, Breaks Writing Clichés, and Inhibits Non-Verbatim Repetition

  123. 58c4b4dfce0d50d482f1c456ed5b526fcccde0df.html#issue-2471950553

  124. Prompting Diverse Ideas: Increasing AI Idea Variance

  125. Pixels Still Beat Text: Attacking the OpenAI CLIP Model With Text Patches and Adversarial Pixel Perturbations

  126. Me, Myself, and AI: the Situational Awareness Dataset (SAD) for LLMs

  127. ce9c8f71ad54707afd165ee5607750648a998a5a.html

  128. Apple or IPod? Easy Fix for Adversarial Textual Attacks on OpenAI's CLIP Model!

  129. design#future-tag-features

    [Transclude the forward-link's context]

  130. 2022-arora-figure4-amapromptgenerationscalingvskshotwithmodelsize.jpg

  131. 2020-roller-facebook-blenderchatbot-ratedperformancevshumans.jpg

  132. https://chat.openai.com/share/04add58f-2052-4b60-ae2a-ab708c29088f

  133. 2687312bcc15ed6e94d5743992fa3defcfecf634.html

  134. https://datajenius.com/2022/02/12/the-effect-of-various-text-generation-methods-on-the-outputs-of-gpt-2/

  135. 0b7acd1fc2fb12765873a242377d6d1bbf3577e9.html

  136. https://github.com/EGjoni/DRUGS

  137. https://github.com/ggerganov/llama.cpp/pull/1773

  138. https://github.com/thomasahle/ziplm

  139. https://homepages.inf.ed.ac.uk/abmayne/publications/sennrich2016NAACL.pdf

  140. https://huggingface.co/blog/constrained-beam-search

  141. 380322510e3f7c82f4226dea0aa7be7612af0b88.html

  142. https://huyenchip.com/2024/01/16/sampling.html

  143. e475aed507923df132e7b3a88c5bea1432cd8cb6.html

  144. https://mi.eng.cam.ac.uk/projects/cued-rnnlm/papers/Interspeech15.pdf

  145. https://news.ycombinator.com/item?id=21335120

  146. be72c2710303c5e973b74c5502b5a982df42de4c.html

  147. https://openai.com/index/introducing-structured-outputs-in-the-api/#_5PYjnV1iAHOPKPupDztdZk

  148. https://sites.google.com/view/medusa-llm

  149. d47fbad81f994a0b9eb15546016239e5cd4805d4.html

  150. https://workshop2015.iwslt.org/downloads/IWSLT_2015_RP_13.pdf

  151. b99a8b4b91b443eb734da6ea291af415d73ab678.pdf

  152. https://www.lesswrong.com/posts/4Hnso8NMAeeYs8Cta/revealing-intentionality-in-language-models-through-adavae#BigVAE_and_Its_Samplers

  153. https://www.trentonbricken.com/Tail-Free-Sampling/

  154. 51d2941c1b4ac4a7ae70204566967847bd61061d.html

  155. https://x.com/voooooogel/status/1865189744776507809

  156. Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

  157. Owain Evans, AI Alignment Researcher

  158. https%253A%252F%252Farxiv.org%252Fabs%252F2407.04694.html

  159. Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass

  160. https%253A%252F%252Farxiv.org%252Fabs%252F2405.18400.html

  161. LLM Evaluators Recognize and Favor Their Own Generations

  162. Sam Bowman

  163. Shi Feng

  164. https%253A%252F%252Farxiv.org%252Fabs%252F2404.13076.html

  165. Re-evaluating GPT-4’s bar exam performance

  166. https%253A%252F%252Flink.springer.com%252Farticle%252F10.1007%252Fs10506-024-09396-9.html

  167. Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

  168. https%253A%252F%252Farxiv.org%252Fabs%252F2403.09629.html

  169. GIVT: Generative Infinite-Vocabulary Transformers

  170. https%253A%252F%252Farxiv.org%252Fabs%252F2312.02116.html

  171. Contrastive Decoding Improves Reasoning in Large Language Models

  172. Mike Lewis

  173. https%253A%252F%252Farxiv.org%252Fabs%252F2309.09117%2523facebook.html

  174. Stay on topic with Classifier-Free Guidance

  175. Stella Biderman

  176. https%253A%252F%252Farxiv.org%252Fabs%252F2306.17806%2523eleutherai.html

  177. Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs

  178. https%253A%252F%252Farxiv.org%252Fabs%252F2306.03081.html

  179. How Language Model Hallucinations Can Snowball

  180. https%253A%252F%252Farxiv.org%252Fabs%252F2305.13534.html

  181. MUX-PLMs: Pre-training Language Models with Data Multiplexing

  182. https%253A%252F%252Farxiv.org%252Fabs%252F2302.12441.html

  183. A survey on text generation using generative adversarial networks

  184. https%253A%252F%252Farxiv.org%252Fabs%252F2212.11119.html

  185. Contrastive Decoding: Open-ended Text Generation as Optimization

  186. Percy Liang

  187. Luke Zettlemoyer

  188. Mike Lewis

  189. https%253A%252F%252Farxiv.org%252Fabs%252F2210.15097.html

  190. Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing (CoPoet)

  191. https%253A%252F%252Farxiv.org%252Fabs%252F2210.13669.html

  192. Contrastive Search Is What You Need For Neural Text Generation

  193. https%253A%252F%252Farxiv.org%252Fabs%252F2210.14140.html

  194. Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models

  195. https%253A%252F%252Farxiv.org%252Fabs%252F2210.15458%2523google.html

  196. Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio

  197. https%253A%252F%252Faclanthology.org%252F2022.cai-1.2.pdf.html

  198. Ask Me Anything (AMA): A simple strategy for prompting language models

  199. https%253A%252F%252Farxiv.org%252Fabs%252F2210.02441.html

  200. Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

  201. About Me

  202. Saurav Kadavath

  203. Andy Jones

  204. Sam Bowman

  205. Sam McCandlish

  206. Jared Kaplan

  207. https://jack-clark.net/about/

  208. https%253A%252F%252Fwww.anthropic.com%252Fred_teaming.pdf.html

  209. Using natural language prompts for machine translation

  210. https%253A%252F%252Farxiv.org%252Fabs%252F2202.11822%2523google.html

  211. Scarecrow: A Framework for Scrutinizing Machine Text

  212. Noah A. Smith

  213. https%253A%252F%252Farxiv.org%252Fabs%252F2107.01294%2523allen.html

  214. Prefix-Tuning: Optimizing Continuous Prompts for Generation

  215. Percy Liang

  216. https%253A%252F%252Farxiv.org%252Fabs%252F2101.00190.html

  217. Bot-Adversarial Dialogue for Safe Conversational Agents

  218. https%253A%252F%252Faclanthology.org%252F2021.naacl-main.235.pdf%2523facebook.html

  219. This Word Does Not Exist

  220. https%253A%252F%252Fwww.thisworddoesnotexist.com%252F.html

  221. Blender: A state-of-the-art open source chatbot

  222. https%253A%252F%252Fai.meta.com%252Fblog%252Fstate-of-the-art-open-source-chatbot%252F.html

  223. Rapformer: Conditional Rap Lyrics Generation with Denoising Autoencoders

  224. https%253A%252F%252Farxiv.org%252Fabs%252F2004.03965.html

  225. Controlling Text Generation with Plug and Play Language Models

  226. https%253A%252F%252Fwww.uber.com%252Fblog%252Fpplm%252F.html

  227. CTRL: A Conditional Transformer Language Model For Controllable Generation

  228. Caiming Xiong—Home Page

  229. Richard Socher

  230. https%253A%252F%252Farxiv.org%252Fabs%252F1909.05858%2523salesforce.html

  231. GPT-2 Neural Network Poetry

  232. Gwern.net Homepage

    [Transclude the forward-link's context]

  233. https://x.com/theshawwn

  234. %252Fgpt-2.html

  235. Language GANs Falling Short

  236. https%253A%252F%252Farxiv.org%252Fabs%252F1811.02549.html