Skip to content
The methodOpen data
Back to the collection

Learning to Generate Reviews and Discovering Sentiment

Alec Radford, Rafal Jozefowicz, Ilya Sutskever

2017 · arXiv

Language models
Read the paper
HN score
0
Mentions
5
Readers
5
Months
5
What’s in a score?

From the abstract

We explore the properties of byte-level recurrent language models. When given sufficient amounts of capacity, training data, and compute time, the representations learned by these models include disentangled features corresponding to high-level concepts. Specifically, we find a single unit which performs sentiment analysis. These representations, learned in an unsupervised manner, achieve state of the art on the binary subset of the Stanford Sentiment Treebank. They are also very data efficient. When using only a handful of labeled examples, our approach matches the performance of strong baselines trained on full datasets. We also demonstrate the sentiment unit has a direct influence on the generative process of the model. Simply fixing its value to be positive or negative generates samples with the corresponding positive or negative sentiment.

Metadata: arXiv. Abstracts retain their original authors’ rights.

In the conversation

Original HN comments, with labels from simple text rules. A label describes the whole comment and may miss context or irony. Read the discussion to make up your own mind. About the labels

5 selected excerpts · 5 total mentions

cmorez
Neutral mention · rule
> [...] but they certainly don't prove what OP claimed. OP's claim was not: "LLMs know whether text is true, false, reliable, or is epistemically calibrated". But rather: "[LLMs condition] on latents *ABOUT* truth, falsity, reliability, and calibration". > It's also very different to ask a model to evaluate the veracity of a nonsense statement, vs. avoiding the generation of a nonsense statement [...] probably could have been done with earlier generations of classifiers Yes. OP's point was not about generation, it was about representation (specifically conditioning on the representation of the [con]text). Your aside about classifiers is not only very apt, it is also…
Read the full comment
exactly OP's point! LLMs are implicit classifiers, and the features they classify have been shown to include those that seem necessary to effectively predict text! One of the earliest examples of this was the so-called ["Sentiment Neuron"](https://arxiv.org/abs/1704.01444), and for a more recent look into kind of features LLMs classify, see [Anthropic's experiments](https://transformer-circuits.pub/2024/scaling-monosemanticit...). > It's obvious from direct experience that they're incapable of knowing true and false in a general sense. Yes, otherwise they would be perfect oracles, instead they're imperfect classifiers. Of course, you could also object that LLMs don't "really" classify anything (please don't), at which point the question becomes how effective they are when used as classifiers, which is what the cited experiments investigate.
Original comment Legal models hallucinate in 1 out of 6 (or more) benchmarking queries
magoghm
Neutral mention · rule
I tried to find the where I heard that Radford was inspired by that blog post, but the closest thing I found is that in the "Sentiment Neuron" paper (Learning to Generate Reviews and Discovering Sentiment: https://arxiv.org/pdf/1704.01444.pdf), in the "Discussion and Future Work" section they mention this Karpathy paper from 2015: Visualizing and Understanding Recurrent Networks https://arxiv.org/abs/1506.02078
Original comment Hi everyone yes, I left OpenAI yesterday
swyx
Neutral mention · rule
i highlighted this last night which seems to be making the rounds - https://twitter.com/swyx/status/1699369076529971545 Alec's CV (https://www.linkedin.com/in/alecradford/) seems to be: - 2011-2016 BSc Eng from Olin College - 2013+ started a data/AI consultancy as a sophomore that turned into a vague startup/product? - 2015 first paper on GANs coauthored with soumith https://arxiv.org/pdf/1511.06434.pdf%C3 - 2016 first GAN paper under openai email https://proceedings.neurips.cc/paper_files/paper/2016/file/8... - 2017 the generative reviews paper mentioend in the Wired article, with Ilya https://arxiv.org/pdf/1704.01444.pdf - 2017 coauthor on PPO paper (precursor to…
Read the full comment
instructgpt/rlhf) https://arxiv.org/pdf/1707.06347.pdf). - 2018 lead author on GPT1 https://www.mikecaptain.com/resources/pdf/GPT-1.pdf - 2019 lead author on GPT2 https://insightcivic.s3.us-east-1.amazonaws.com/language-mod... blog https://openai.com/research/better-language-models - 2019 coauthor on RLHF https://arxiv.org/pdf/1909.08593.pdf) - 2020 coauthor on gpt3 https://arxiv.org/abs/2005.14165 - 2020 coauthor on scaling laws https://arxiv.org/pdf/2001.08361.pdf%E4%B8%AD%E5%BE%97%E5%88... - 2021 coauthor on DallE http://proceedings.mlr.press/v139/ramesh21a/ramesh21a.pdf - 2021 coauthor on Codex https://arxiv.org/pdf/2107.03374.pdf?trk=public_post_comment... - 2023 lead author on Whisper https://proceedings.mlr.press/v202/radford23a/radford23a.pdf name a more successful 7 year CS career post undergrad... Update: FYI openai just announced a "developer day" in Nov - somehow not blessed by the HN gods https://news.ycombinator.com/item?id=37408234
Original comment What OpenAI Really Wants
tensor
Neutral mention · rule
Sure, in looking at what it would cost to replicate this: https://arxiv.org/pdf/1704.01444.pdf They say they used four Titan X cards for a month. I was actually looking at google cloud machine learning since I thought being targeted to tensorflow would be the most cost effective. But it's 0.49/hour per ML training unit, or 1.47/hour per GPU. A basic gpu gives 3 training units, so I thought that something approximately similar would require 12 training units, which comes to something like $4000+ a month. Maybe I completely misunderstood the resources being offered though, because you are right that cloud engine costs seem much lower. I'll have to revisit the math here,…
Read the full comment
though it worries me that it's not at all clear that a K80 will be much faster than a Titan X for a given problem. E.g. https://www.amax.com/blog/?p=907. It would also be really nice to get some pricing and benchmarks for the new TPUs, assuming they are priced better. Maybe part of the problem is that vendors are not making it remotely easy to even understand what performance you'll actually get for a given price.
Original comment Which GPU(s) to Get for Deep Learning
tshadley
Neutral mention · rule
"The selected model reaches 1.12 bits per byte." (https://arxiv.org/pdf/1704.01444.pdf) For context, Claude Shannon found that humans could model English text with an entropy of 0.6 to 1.3 bits per character (http://languagelog.ldc.upenn.edu/myl/Shannon1950.pdf)
Original comment Unsupervised sentiment neuron

Keep following the thread.

More in Language models

More from the same topics.