arXiv (All)
open access
DeltaTrace: Efficient Signed Attribution for Reasoning Language Models
We study how words in the context support or oppose a language model's response and present DeltaTrace, a novel attribution framework that explains the effect of input tokens on a fixed model response. DeltaTrace measures how the response's log-probability changes when the context tokens being expla
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Truncated Reasoning Under a Budget: Evaluating System-1 Models as Decision-makers#1400588
- What Kind of Reasoning (if any) is an LLM actually doing? On the Stochastic Nature and Abductive Appearance of Large Language Models#701151
- Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability#1188187
- Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability#1181686
- Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning#1187310
Record · ID 1401069
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive