Search papers, labs, and topics across Lattice.
3
0
6
2
Consensus reasoning through structured DAG aggregation reveals hidden insights in LLM outputs, outperforming traditional methods and providing a transparent view of model reasoning.
LLMs can be detoxified with minimal performance impact by surgically intervening on a small subset of attention heads causally linked to toxicity, identified via a novel causal inference approach.
LLM-based query rewriting in RAG can reduce retrieval bias by over 50%, but breaks down when biases combine adversarially, revealing the limits of query-side interventions.
