Feedback as an Interface: Controlling Form and Detail in LLM Translation Refinement
cs.CL
Submitted: 2026-10-11
Updated: 2026-10-11
Project page: https://www.bundestag.de/en/service/legal_notice
Sources
- MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
- AI safety via debate
- MALT: Improving Reasoning with Multi-Agent LLM Training
- Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents
- Refining the Responses of LLMs by Themselves
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering