What Lilian Weng thinks about LLMs
Machine-learning researcher; has written the Lil'Log survey posts on how a model technique works since 2017, and worked at OpenAI from 2018 to 2024.
Lilian Weng did not write this page.
We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.
Filter LLMs · Newest first
Only Lilian Weng on LLMs. See everyone on LLMs
10 dated positions, 2023 to 2026, in their own words. Our reading of what Lilian Weng has said — not written or endorsed by them.
-
Our readingThe deployment layer surrounding a model is as important as the model's raw intelligence.
Their wordsthe layer between the raw model and the real-world context seems to be as important as the model's raw intelligence
↗Harness Engineering for Self-Improvementlilianweng.github.io 1st of 3 in this piece
-
Their wordsharness improvement enables better deployment of the model but intelligence is still the core.
↗Harness Engineering for Self-Improvementlilianweng.github.io 3rd of 3 in this piece
- 10 days earlier
-
Our readingAs models keep growing, AI is running out of enough high-quality unique training tokens to keep up.
Their wordsAs the model size grows significantly, we are running out of enough high-quality unique tokens.
- 14 months earlier
-
Our readingLarge language models cannot reliably self-correct their own mistakes without external feedback.
Their wordsthis self-correction capability turns out to not exist intrinsically among LLMs and does not easily work out of the box, due to various failure modes
-
Our readingLonger test-time thinking improves an AI model's robustness to adversarial or unusual inputs.
Their wordsthinking for longer should be especially useful when the model is presented with an unusual input, such as an adversarial example or jailbreak attempt
-
Their wordsmodel CoTs could be biased due to lack of explicit training objectives aimed at encouraging faithful reasoning
- 10 months earlier
-
Their wordsTo avoid hallucination, LLMs need to be (1) factual and (2) acknowledge not knowing the answer when applicable.
↗Extrinsic Hallucinations in LLMslilianweng.github.io 1st of 2 in this piece
-
Their wordsThese empirical results from Gekhman et al. (2024) point out the risk of using supervised fine-tuning for updating LLMs' knowledge.
↗Extrinsic Hallucinations in LLMslilianweng.github.io 2nd of 2 in this piece
- 8 months earlier
-
Their wordsOne drawback with UAT (Universal Adversarial Trigger) attacks is that it is easy to detect them because the learned triggers are often nonsensical.
↗Adversarial Attacks on LLMslilianweng.github.io 1st of 2 in this piece
-
Their wordsHigh perplexity makes an attack more vulnerable to be detected and mitigated.
↗Adversarial Attacks on LLMslilianweng.github.io 2nd of 2 in this piece