John Wieting Profile
John Wieting

@johnwieting2

Followers
549
Following
2K
Media
2
Statuses
105

Senior Research Scientist @GoogleDeepMind 🧠. PhD @LTIatCMU.

Joined December 2015
Don't wanna be here? Send us removal request.
@johnwieting2
John Wieting
9 months
Work led by @YapeiChang with @kalpeshk2011, @houmansadr, myself, and @MohitIyyer. Work done at @manningcics, @UMassNLP with collaboraters from @GoogleAI, @GoogleDeepMind. #NLProc.
0
0
4
@johnwieting2
John Wieting
9 months
Paper: Code:
1
0
1
@johnwieting2
John Wieting
9 months
Interested in robust watermarks for detecting LLM-generated text that do not require logit access to the underlying models? Check out our new paper to be presented at @emnlpmeeting! We propose PostMark, a black-box watermarking scheme that is more robust to paraphrasing attacks.
@YapeiChang
Yapei Chang
1 year
Is it possible to have a watermark that reliably detects LLM-generated text, is robust to paraphrasing attacks, preserves quality, and can be applied to any LLM without access to logits? Check out PostMark, a method with all these properties!. . 🧵below:
Tweet media one
1
2
12
@johnwieting2
John Wieting
9 months
This was work done at @GoogleDeepMind @GoogleAI. #NLProc.
0
0
0
@johnwieting2
John Wieting
9 months
Check out our new paper1 We propose a watermarking scheme for LLMs that works with black-box access, is distortion-free, has provable guarentees, and can be chained with secret keys. Able to outperform white-box methods in comprehensive experiments.
1
11
52
@johnwieting2
John Wieting
1 year
Congratulations to UMD!.
@umdcs
UMD Department of Computer Science
1 year
.@UofMaryland's CS dept is welcoming eight new tenure-track faculty members! With expertise in cutting-edge areas, they'll boost our academic & research capabilities. Welcome aboard! 🐢📚. Read more:.
Tweet media one
0
0
2
@johnwieting2
John Wieting
1 year
RT @YapeiChang: Is it possible to have a watermark that reliably detects LLM-generated text, is robust to paraphrasing attacks, preserves q….
0
28
0
@johnwieting2
John Wieting
1 year
RT @nandan__thakur: Excited to share that SWIM-IR has been accepted at #NAACL2024! 🍻. I'm quite delighted with this work as it was complete….
0
3
0
@johnwieting2
John Wieting
1 year
There are so many accounts (bots?) on X/Twitter posting ChatGPTish responses or the same irrelevant responses across posts. It seems fairly obvious how these could be filtered out. I wonder why nothing is done. I thought it'd improve over time, but it really hasn't.
0
0
4
@johnwieting2
John Wieting
1 year
RT @aclmeeting: ACL announcement: ."The ACL Executive Committee has voted to significantly change ACL's approach to protecting anonymous pe….
0
186
0
@johnwieting2
John Wieting
2 years
This was work done both at @GoogleAI and @UMassAmherst with @kalpeshk2011, @yixiao_song, @mar_kar_, @MohitIyyer, and myself. #NLProc.
0
0
1
@johnwieting2
John Wieting
2 years
Arxiv: Models (Hugging Face versions strongly recommended): . Code:
1
0
1
@johnwieting2
John Wieting
2 years
Come by our poster this evening! @kalpeshk2011, @yixiao_song, and I will be presenting. Links to paper and models below 👇.
1
0
1
@johnwieting2
John Wieting
2 years
3. A state-of-the-art paraphrasing model that paraphrases long-form text, can use context to paraphrase text within delimiters, controls output output lexical and syntactic diversity, and is validated by copious human evaluations . .
1
0
2
@johnwieting2
John Wieting
2 years
Today at #NeurIPS2023, If you want to lean more about:. 1. Robustness of detectors and watermarks to paraphrase attacks (spoiler alert: needs improvement). 2. An alternative detection approach using simple retrieval methods. and . .
@kalpeshk2011
Kalpesh Krishna
2 years
To detect text written by LMs like #ChatGPT, many methods have recently emerged: DetectGPT, watermarks, GPTZero. We present a paraphrasing attack that can drop their detection rates to <10%. To defend against it, we propose detection with retrieval. 🧵👇
Tweet media one
1
4
20
@johnwieting2
John Wieting
2 years
This dataset can be used to train multilingual/cross-lingual attribution models and evaluate LLMs in few-shot multilingual/cross-lingual settings (which is becoming increasingly important), among other uses. This was work done at @GoogleAI. #NLProc.
1
0
1
@johnwieting2
John Wieting
2 years
Our work on cross-lingual and multilingual attribution will be presented at #EMNLP2023 in Singapore!. We have also released our dataset of ~10k 3-way annotations over 5 typologically diverse languages. Arxiv: Dataset:
@johnwieting2
John Wieting
2 years
We all want accurate responses from our QA systems, and this need becomes especially vital when interacting with text in languages unfamiliar to us, rendering answer verification reliant on translation. This challenge is particularly felt by speakers of low-resource languages.
1
8
24
@johnwieting2
John Wieting
2 years
RT @ben_mlr: Excited to be presenting our work on.**Evaluating and Modeling Attribution for Cross-Lingual Question Answering** at #EMNLP202….
0
5
0
@johnwieting2
John Wieting
2 years
Later today:. Sam Altman: "I'm pleased to announce I'm looking to raise venture capital for my new startup: ClosedAI.".
2
0
6
@johnwieting2
John Wieting
2 years
RT @sunjiao123sun_: Can LLMs generate exact 5 words? No.How about 5 sentences? No.How about 5 paragraphs? No.🤷🏻‍♀️.In .
0
77
0