AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

BigScience Workshop

JMLR 2024 · Large language models › Language, safety and interpretability · approach: Multilingual LLM data and culture · 2,860 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use multilingual byte-level BPE tokenizer instead of monolingual tokenizerBLOOM tokenizer · Universal Dependencies 2.9 (fr)fertility: 1.30 -> 1.17 (-11%)Improved
use multilingual byte-level BPE tokenizer instead of monolingual tokenizerBLOOM tokenizer · Universal Dependencies 2.9 (ar)fertility: 1.16 -> 1.34 (+13%)Hurt
use multilingual byte-level BPE tokenizer instead of monolingual tokenizersBLOOM tokenizer · Universal Dependencies 2.9 (6 languages)fertility: fr -11%, en +0%, es +3%, zh +5%, hi +9%, ar +13%Mixed
add unicode NFKC normalization to the tokenizer (ablation)BLOOM tokenizer · fertility on considered languagesfertility: did not reduce fertility by more than 0.8%No clear effect
use causal decoder-only architecture instead of encoder-decoder or other objectives (ablation)pretraining architecture · zero-shot generalization (EAI-Eval, T0-Eval)zero-shot performanceImproved
use ALiBi positional embeddings instead of learned or rotary embeddings (ablation)BLOOM (1.3B ablation) · zero-shot downstream tasksdownstream performance and training smoothnessImproved
add embedding LayerNorm after the embedding layer (ablation)BLOOM 104B preliminary · training stability and zero-shot generalizationstability / zero-shot performanceMixed
deduplicate lines in tokenizer training data (ablation)BLOOM tokenizer · tokenizer vocabulary qualityvocabulary qualityImproved
use a 250k vocabulary instead of 150k (ablation)BLOOM tokenizer · fertility vs monolingual tokenizersfertilityImproved
train in bfloat16 instead of float16BLOOM 176B · training stabilitystabilityImproved

Later papers that compared with this method

3 later accepted papers report BLOOM 560M as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy