pith. sign in

Title resolution pending

Use the insider to gain access to sensitive information, systems

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

citation-role summary

method 1

citation-polarity summary

use method 1

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

roles

method 1

polarities

use method 1

representative citing papers

One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety

cs.CL · 2026-04-01 · unverdicted · novelty 7.0

Incremental Completion Decomposition (ICD) jailbreaks LLMs via sequences of single-word continuations before full harmful responses, outperforming existing methods on AdvBench, JailbreakBench, and StrongREJECT with supporting mechanistic analysis.

citing papers explorer

Showing 1 of 1 citing paper.

  • One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety cs.CL · 2026-04-01 · unverdicted · none · ref 5

    Incremental Completion Decomposition (ICD) jailbreaks LLMs via sequences of single-word continuations before full harmful responses, outperforming existing methods on AdvBench, JailbreakBench, and StrongREJECT with supporting mechanistic analysis.