Large language models (LLMs) are increasingly used in modern search and answer systems to synthesize multiple, sometimes conflicting, texts into a single response, yet current pipelines offer weak incentives for sources to be accurate and are vulnerable to adversarial content. We introduce Truthful Text Summarization (TTS), an incentive-aligned framework that improves factual robustness without ground-truth labels. TTS (i) decomposes a draft synthesis into atomic claims, (ii) elicits each source's stance on every claim, (iii) scores sources with an adapted multi-task peer-prediction mechanism that rewards informative agreement, and (iv) filters unreliable sources before re-summarizing. We establish formal guarantees that align a source's incentives with informative honesty, making truthful reporting the utility-maximizing strategy. Experiments show that TTS improves factual accuracy and robustness while preserving fluency, aligning exposure with informative corroboration and disincentivizing manipulation.

翻译：大语言模型（LLM）在现代搜索与问答系统中日益广泛地用于将多篇（有时相互矛盾的）文本综合为单一响应，然而现有流程对信息来源的准确性激励不足，且易受对抗性内容影响。本文提出真实文本摘要（TTS），一种无需真实标签即可提升事实鲁棒性的激励对齐框架。TTS通过以下步骤实现：（i）将草稿综合分解为原子主张，（ii）获取每个信息源对每个主张的立场，（iii）采用改进的多任务同伴预测机制对信息源进行评分（该机制奖励信息性一致），（iv）在重新摘要前过滤不可靠信息源。我们建立了形式化保证，使信息源的激励与信息性诚实对齐，令真实报告成为效用最大化策略。实验表明，TTS在保持流畅性的同时提升了事实准确性与鲁棒性，使信息曝光与信息性佐证对齐，并有效抑制操纵行为。