Farid Adilazuarda
@faridlazuarda
Followers
281
Following
41K
Media
162
Statuses
3K
Incoming PhD @EdinburghNLP @InfAtEd • Efficient & Multilingual LLMs • prev: @mbzuai @itbofficial
Joined October 2017
Can English-finetuned LLMs reason in other languages?. Short Answer: Yes, thanks to “quote-and-think” + test-time scaling. You can even force them to reason in a target language!. But:.🌐 Low-resource langs & non-STEM topics still tough. New paper:
arxiv.org
Reasoning capabilities of large language models are primarily studied for English, even when pretrained models are multilingual. In this work, we investigate to what extent English reasoning...
📣 New paper!. We observe that reasoning language models finetuned only on English data are capable of zero-shot cross-lingual reasoning through a "quote-and-think" pattern. However, this does not mean they reason the same way across all languages or in new domains. [1/N]
1
6
34
RT @DimitrisPapail: GRPO makes reasoning model yap a lot, but there's a simple fix:. Sample more responses during training, and train on th….
0
31
0
Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.
393
663
3K
RT @AlessandroStru4: The best logical explanation of entropy. (It only took me 11 months to find an hour to read it). .
arxiv.org
This short book is an elementary course on entropy, leading up to a calculation of the entropy of hydrogen gas at standard temperature and pressure. Topics covered include information, Shannon...
0
317
0
RT @barcacentre: Rashford: "All of the lads are like young, if you're like 27, 28, I'd say there's more players under 21 than past 28. In m….
0
58
0
RT @khoomeik: my gpt-oss MFUmaxxer PR is here!. ✅ cat/splice sink -> flexattn.✅ sin/cos pos embs -> complex freqs_cis.✅ moe for-loop -> gro….
0
13
0
RT @ilyasut: if you value intelligence above all other human qualities, you’re gonna have a bad time.
0
2K
0
RT @JackFrostHeeHo9: @TheNewRhyme If they are your friend they wouldn’t let a disagreement ruin a friendship.
0
778
0
RT @jxmnop: curious about the training data of OpenAI's new gpt-oss models? i was too. so i generated 10M examples from gpt-oss-20b, ran….
0
522
0
I will always cherish "ada indonesia coy!" moments like these. So proud!🇮🇩🙌
And congratulations to 🇮🇩Indonesia for winning 3 Silvers (Faiz, Matthew, Luvidi) and 1 Bronze (Jayden)!. A strong debut for Indonesia’s first participation, hope to see even more in the future!
0
0
10
RT @AlhamFikri: And congratulations to 🇮🇩Indonesia for winning 3 Silvers (Faiz, Matthew, Luvidi) and 1 Bronze (Jayden)!. A strong debut for….
0
88
0
RT @Guangxuan_Xiao: I've written the full story of Attention Sinks — a technical deep-dive into how the mechanism was developed and how our….
0
264
0
RT @sporadicalia: just remembered that time Noam Shazeer dropped the hardest line ever written in an ML paper
0
623
0
RT @wenhaocha1: Deep dive into Sink Value in GPT-OSS models! .Analyzed 20B (24 layers) and 120B (36 layers) models and found (correct me if….
0
17
0
RT @gu_xiangming: I noticed that @OpenAI added learnable bias to attention logits before softmax. After softmax, they deleted the bias. Thi….
0
174
0
RT @dvruette: gpt-oss is probably the most standard MoE transformer that ever was. Couple of details worth noting:.- Uses attention sinks (….
0
77
0
0
437
0
RT @dnystedt: Four TSMC 2nm fabs will be in mass production next year and monthly capacity over 60,000 wafers-per-month (wpm), media report….
0
52
0