EMNLP paper uses sparse autoencoders for text-based causal confounding adjustment
anjalie_f · x · 2026-10-27
Mian Zhong presents "Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment" at EMNLP on Oct 27 (9 AM).
The work targets causal questions that hinge on text — e.g., whether the type of media coverage of a bill affects how many legislators vote for it — using sparse autoencoders (SAEs) to adjust for text-based causal confounders.
More from Research
- Scientists argue research scaling is 80% one-pot protocols, not lab automation — clarejtbirch · 2026-10-27
- Yoav Artzi simulates 4 capped-reviewing mechanisms on real COLM data: 12-24% of accepted papers left out — yoavartzi · 2026-10-27
- Experiment finds 9 'gender neurons' in Qwen3.5-4B that flip its self-identity — burny_tech · 2026-10-27
- GPT-6-Astra embodied intelligence eval: near-100% on several of 12 benchmarks — chris_j_paxton · 2026-10-27
- LEANN open-source RAG project claims 97% vector DB storage savings: 201GB to 6GB — Promptmethus · 2026-10-27
- Claude Opus 5.5 claims ETH false, all-dimension Kakeya and Yang-Mills in one day — repligate · 2026-10-27