Cool tutorial on using flan t5!
LLMS
-
Bing Chat vs ChatGPT: Personality Differences and Closed-Source Limitations
By
–
bing chat seems to have really quite a different « personality » than chatGPT does it comes from the model and training data, how it’s used and integrated or users interactions we’ll likely just never know why since it’s all closed source research and deployment
-
Family Tree of Transformer Models Evolution and Convergence
By
–
A beautiful "family tree" of large Transformer models from Vaswani et al's 2017 design So cool to see the lineages from GPT, BERT, T5, and PaLM develop and Diffusion models starting from a different place but converging with CLIP and ViT.
-
Why Chatbots Malfunction: Understanding AI Limitations and Safeguards
By
–
Let's get real. This is why chatbots sometimes act weird and spout nonsense — and why companies can't completely stop it:
-
ChatGPT Explanation: Impressive But Not Revolutionary
By
–
@stephen_wolfram gives a necessarily long but very good explanation of what and how chatGPT works. My view: calm down people. There are important things there but not the shiny "world has changed for ever" techno-salvation that many people pining for.
-
Large Language Models RLHF Ethics Natural Language Principles
By
–
This work and CAI both observe the same basic phenomenon: if language models are sufficiently large and we add enough RLHF to make them helpful, we can more effectively get them to abide by high-level ethical principles expressed in natural language.
-
Cautious Optimism on the Ethics of Language Models
By
–
We believe our results are cause for cautious optimism regarding the ability to train language models to abide by ethical principles, echoing encouraging results we saw in our earlier related work on Constitutional AI (CAI).
-
RLHF and Prompting Techniques for Targeted Model Behavior
By
–
This means that if we have a target behavior (e.g. non-discrimination) we may be able to nudge models to achieve that target using IF/CoT prompting if RLHF alone is not sufficient. But we must be careful to check whether RLHF + prompting causes the models to overshoot the target.
-
Language Models Show Demographic Bias Tradeoffs in Decision Making
By
–
Prompting models to avoid making decisions based on race achieves demographic parity at steps 300 (CoT) and 600 (IF) but causes the model to start to discriminate against white students at higher steps. (Note that we do not claim LMs should be used for automated decision making!)
-
RLHF Training Reduces but Doesn’t Eliminate Racial Discrimination in Admissions
By
–
Finally, we develop a benchmark testing for racial discrimination in LM decision-making in student course admissions. In our control condition (blue) we find more RLHF training produces model outputs that approach demographic parity but still discriminates against Black students.