Human-Oriented Binary Reverse Engineering (HOBRE) lies at the intersection of binary and source code, aiming to lift binary code to human-readable content relevant to source code, thereby bridging the binary-source semantic gap. Recent advancements in uni-modal code model pre-training, particularly in generative Source Code Foundation Models (SCFMs) and binary understanding models, have shown promise. However, existing approaches for HOBRE rely heavily on uni-modal models like SCFMs for supervised fine-tuning or general LLMs for prompting, resulting in sub-optimal solutions. Inspired by recent progress in multi-modal models, we argue that it is possible to harness the strengths of both uni-modal code models to bridge the semantic gap effectively. In this paper, we propose a novel probe-and-recover framework that incorporates a binary-source encoder-decoder model and black-box LLMs for binary analysis. Our approach leverages the pre-trained knowledge within SCFMs to synthesize relevant, symbol-rich code fragments as context. This additional context enables black-box LLMs (recoverers) to enhance recovery accuracy. We demonstrate significant improvements in zero-shot binary summarization and binary function name recovery, with a 10.3\% relative gain in CHRF and a 16.7\% relative gain in a GPT4-based metric for summarization, as well as a 6.7\% and 7.4\% absolute increase in token-level precision and recall for name recovery, respectively. These results highlight the effectiveness of our approach in automating and improving binary code analysis.