Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal structure of LLMs by training sparse autoencoders to learn a sparse representation of the query embedding, allowing precise control over the model's attention distribution. We demonstrate that manipulating this sparse representation effectively transforms the output toward different stylistic and cognitive targets. Specifically, in an educational setting, we show that the cognitive complexity of LLM-generated feedback can be systematically adjusted by modifying the encoded query representation at a specific layer. To achieve this, we guide the learned sparse embedding toward the representation of samples from the desired cognitive complexity level, using gradient-based optimization in the latent space.

Our work utilizes Summarization is the consolidated format for a learning of these semantic concepts as an intermediate large document and has been widely used for step from the videos. These semantic concepts many applications i.e., understanding a long meeting/event, along with the transcriptions (semantic augmentation) story summarization etc. Abstractive as input to a pre-trained summarizer model summarization is challenging in the Natural Language enrich the performance. In this work, we address Generation(NLG) domain as it requires an the problem of (i) generating semantically relevant understanding of all the salient information in annotations of a video (semantic concepts) using a the input document and rewriting logically in a fixed number of sampled frames from each video condensed manner rather than selection (extractive).