Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambiguous or open-ended user requests, failing to help users reach their ultimate intents and leading to inefficient conversations. To address these limitations, we introduce CollabLLM, a novel and general training framework that enhances multiturn human-LLM collaboration. Its key innovation is a collaborative simulation that estimates the long-term contribution of responses using Multiturn-aware Rewards. By reinforcement fine-tuning these rewards, CollabLLM goes beyond responding to user requests, and actively uncovers user intent and offers insightful suggestions—a key step towards more human-centered AI. We also devise a multiturn interaction benchmark with three challenging tasks such as document creation. CollabLLM significantly outperforms our baselines with averages of 18.5% higher task performance and 46.3% improved interactivity by LLM judges. Finally, we conduct a large user study with 201 judges, where CollabLLM increases user satisfaction by 17.6% and reduces user spent time by 10.4%.

DNS manipulation is an increasingly common technique used by censors and other network adversaries to prevent users from accessing restricted Internet resources and hijack their connections. Prior work in detecting DNS manipulation relies largely on comparing DNS resolutions with trusted control results to identify inconsistencies. However, the emergence of CDNs and other cloud providers practicing content localization and load balancing leads to these heuristics being inaccurate, paving the need for more verifiable signals of DNS manipulation. In this paper, we develop a new technique, CERTainty, that utilizes the widely established TLS certificate ecosystem to accurately detect DNS manipulation, and obtain more information about the adversaries performing such manipulation. We find that untrusted certificates, mismatching hostnames, and blockpages are powerful proxies for detecting DNS manipulation. Our results show that previous work using consistency-based heuristics is inaccurate, allowing for 72.45% false positives in the cases detected as DNS manipulation. Further, we identify 17 commercial DNS filtering products in 52 countries, including products such as SafeDNS, SkyDNS, and Fortinet, and identify the presence of 55 ASes in 26 countries that perform ISP-level DNS manipulation. We also identify 226 new blockpage clusters that are not covered by previous research. We are integrating techniques used by CERTainty into active measurement platforms to continuously and accurately monitor DNS manipulation.