AI Paper Atlas

Research map / Large language models

Language, safety and interpretability: research map

3,002 papers on Language, safety and interpretability in Large language models, from ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR (2016–2026), grouped into 6 clusters and 26 approaches. The busiest year so far is 2026.

What it is

What happens inside language models and how to make them safe: interpretability studies how attention heads and representations encode knowledge; safety work covers jailbreaks, unlearning, bias, watermarking and detecting machine-written text; other work covers multilingual and speech models.

Terms you will see on this page:

Mechanistic interpretability
reverse-engineering the circuits a network uses.
Jailbreak
a prompt that makes a model ignore its safety rules.
Text watermarking
hiding a statistical signal in generated text so it can be detected later.

Start reading with the most cited papers here:

Within Large language models, its share shrank from 35.2% in 2023–24 to 26.9% in 2025–26 (700 → 1,847 papers at ICML, NeurIPS, ICLR, CVPR and AAAI, the venues with data for all four years).

2016: 12162017: 12172018: 42182019: 52192020: 80202021: 98212022: 106222023: 195232024: 528242025: 843252026: 103426

Explore Language, safety and interpretability in the interactive map

Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.

What changed recently

Approaches whose share of the topic moved most between 2023–24 and 2025–26 (ICML, NeurIPS, ICLR, CVPR and AAAI):

Papers from 2025–2026 that are already cited most:

Approaches and key papers

Prompting, evaluation and in-context learning · 1,330 papers
Keywords: prompt, uncertainty, shot

Approaches in this cluster:

Most cited and most cited since 2024:

Inside LLM representations · 458 papers
Keywords: languages, pretraining, multilingual

Approaches in this cluster:

Most cited and most cited since 2024:

Language generation, speech and multilingual models · 414 papers
Keywords: natural language, speech, generation

Approaches in this cluster:

Most cited and most cited since 2024:

Jailbreaks, bias and uncertainty · 343 papers
Keywords: safety, jailbreak, harmful

Approaches in this cluster:

Most cited and most cited since 2024:

Watermarking and detecting AI text · 231 papers
Keywords: watermarking, generated text, watermarks

Approaches in this cluster:

Most cited and most cited since 2024:

Interpretability and safety alignment · 226 papers
Keywords: representations, interpretability, heads

Approaches in this cluster:

Most cited and most cited since 2024:

Related topics in Large language models

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