Automatic Survey Generation (ASG) aims to produce comprehensive literature surveys by retrieving, organizing, and synthesizing academic papers. Despite rapid progress in specialized ASG frameworks and Deep Research agents, existing evaluations largely center on Computer Science or rely on generic criteria, leaving it unclear whether current systems satisfy the survey standards of diverse disciplines. We introduce SurveyLens, the first discipline-aware ASG benchmark. SurveyLens comprises SurveyLens-1k, a curated dataset of 1,000 human-written surveys across 10 disciplines, and a dual-lens framework that combines discipline-aware rubric scoring with reference-based alignment to human-written surveys. Evaluating 11 state-of-the-art systems spanning vanilla LLMs, specialized ASG systems, and Deep Research agents, we find that Deep Research agents perform most consistently across the 10 disciplines, some specialized ASG systems show particular strength in outline generation, and reference coverage and relevance remain a shared bottleneck across paradigms. These findings further provide practical guidance for discipline-specific system selection and future ASG design.

Sentiment transfer aims to change the underlying sentiment of input sentences. The two major challenges in existing works lie in (1) effectively disentangling the original sentiment from input sentences; and (2) preserving the semantic content while transferring the sentiment. We find that identifying the sentiment-irrelevant content from input sentences to facilitate generating output sentences could address the above challenges and then propose the Decode with Template model in this paper. We first mask the explicit sentiment words in input sentences and use the rest parts as templates to eliminate the original sentiment. Then, we input the templates and the target sentiments into our bidirectionally guided variational auto-encoder (VAE) model to generate output. In our method, the template preserves most of the semantics in input sentences, and the bidirectionally guided decoding captures both forward and backward contextual information to generate output. Both two parts contribute to better content preservation. We evaluate our method on two review datasets, Amazon and Yelp, with automatic evaluation methods and human rating. The experimental results show that our method significantly outperforms state-of-the-art models, especially in content preservation.