Paper: topic models move from word counts to context for asset pricing
PtrPomorski · x · 2026-10-03
The paper 'From Word Counts to Context: Topic Models for Asset Pricing' applies context-aware topic models—going beyond raw word counts—to asset pricing, showing how richer NLP methods can improve text-based financial factors.
More from Research
- Meta paper: RL post-training hurts test-time scalability — the 'Sharpening Tax' — dair_ai · 2026-10-04
- Review Papers Without Strong Opinions Are Dead, Says Researcher; AI Slashes Data-Collection Work — jwt0625 · 2026-10-04
- AutoCompact trains agents to compact context themselves, +9.2 on SWE-bench Verified — omarsar0 · 2026-10-04
- ICLR 2027 trims review scores to a 4-point scale, reviewers puzzled — random-tomato · 2026-10-04
- EPFL paper recasts multi-view stereo as seq2seq, beating MVS and feed-forward baselines — CSProfKGD · 2026-10-03
- New COLM paper shows "forks in the road" in post-training data shrink reasoning models' coverage — ParshinShojaee · 2026-10-03