finding
active
finding:dpo-raises-hallucinated-urls-from-37-to-412-regex-filter-reduces-to-354DPO raises hallucinated URLs from 37 to 412; regex filter reduces to 354
Table 11.
Source paper
extracted_from(2026) · Leon Bergen · Usha Bhalla · Sidharth Baskaran · Max Loeffler +13
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Related-work discussion.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Benchmark identification rate rises from 0.08 (SFT) to 0.25 (DPO); interventions barely reduce itfinding0.751Table 11.
- After DPO stage, VS outperforms direct prompting by 182.6% on diversity in poem continuation using Tulu-70Bfinding0.744Demonstrates the magnitude of VS's advantage over direct prompting after aggressive alignment training
- Quantifies how much of the base model's diversity VS can recover compared to baseline prompting
- Table 11.
- Key observation that SP rankings are preserved cross-architecturally while AS is not
- Prompt-conditioned pipeline predicts DPO-induced feature change with R²=0.58 on Llama-3.1-8B/Dolcifinding0.729Fig. 7 validation.
- Reasoning model vulnerability under prompting
- Feature-conditioned pipeline predicts DPO-induced feature change with R²=0.9 on Llama-3.1-8B/Dolcifinding0.723Fig. 6 validation.