CMU paper: Cross-topic name collisions in AI papers are surging, hurting retrieval
CarnegieMellonU · hf · 2026-11-09
Carnegie Mellon University published a paper on Hugging Face titled "'PRISM' Is Not All You Need", studying cross-topic name collisions in AI research papers. As the volume of AI papers has surged, papers sharing the same name across different topics have risen sharply, and they remain hard to identify even with research clues. Language-model-based ranking improves matching accuracy.
More from Research
- New benchmarks DecoyCount and ScienceVision probe whether AI sees or reasons — liangchen5518 · 2026-11-09
- AI chip design demo: one prompt for a 64-bit RISC-V processor under 3W TDP — satnam6502 · 2026-11-09
- Video-guided machine translation paper lifts low-resource Indic languages by +1.75 BLEU — kalyan_kpl · 2026-11-09
- Peer-reviewed paper applies truth maintenance systems to LLM memory belief revision — letandrewcook · 2026-11-09
- A cathedral that sings: 1D acoustic sim shows voices fighting their own resonant body — Sauers_ · 2026-11-09
- Survey by 30+ authors maps modern NLP tokenization, from subword wins to its flaws — rdesh26 · 2026-11-09