ASAbishek Sridhar

Abishek Sridhar

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Abishek Sridhar has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Hierarchical Prompting Assists Large Language Model on Web Navigation

    by Abishek Sridhar, Robert Lo, Frank F. Xu, Hao Zhu, Shuyan Zhou

    Large language models (LLMs) struggle on processing complicated observations in interactive decision making tasks. To alleviate this issue, we propose a simple hierarchical prompting approach. Diverging from previous prompting approaches that always put the full observation (e.g. a web page) to the prompt, we propose to first construct an action-aware observation which is more condensed and relevant with a dedicated SUMMARIZER prompt. The ACTOR prompt then predicts the next action based on the summarized observation. While our method has broad applicability, we particularly demonstrate its efficacy in the complex domain of web navigation where a full observation often contains redundant and irrelevant information. Our approach outperforms the previous state-of-the-art prompting mechanics by 6.2% on task success rate, demonstrating its potential on interactive decision making tasks with long observation traces.

  • Open Access

    Exploring the Role of the Bottleneck in Slot-Based Models Through Covariance Regularization

    by Andrew Stange, Robert Lo, Abishek Sridhar, Kousik Rajesh

    In this project we attempt to make slot-based models with an image reconstruction objective competitive with those that use a feature reconstruction objective on real world datasets. We propose a loss-based approach to constricting the bottleneck of slot-based models, allowing larger-capacity encoder networks to be used with Slot Attention without producing degenerate stripe-shaped masks. We find that our proposed method offers an improvement over the baseline Slot Attention model but does not reach the performance of \dinosaur on the COCO2017 dataset. Throughout this project, we confirm the superiority of a feature reconstruction objective over an image reconstruction objective and explore the role of the architectural bottleneck in slot-based models.

  • Open Access

    LIC-GAN: Language Information Conditioned Graph Generative GAN Model

    by Robert Lo, Arnhav Datar, Abishek Sridhar

    Deep generative models for Natural Language data offer a new angle on the problem of graph synthesis: by optimizing differentiable models that directly generate graphs, it is possible to side-step expensive search procedures in the discrete and vast space of possible graphs. We introduce LIC-GAN, an implicit, likelihood-free generative model for small graphs that circumvents the need for expensive graph matching procedures. Our method takes as input a natural language query and using a combination of language modelling and Generative Adversarial Networks (GANs) and returns a graph that closely matches the description of the query. We combine our approach with a reward network to further enhance the graph generation with desired properties. Our experiments, show that LIC-GAN does well on metrics such as PropMatch and Closeness getting scores of 0.36 and 0.48. We also show that LIC-GAN performs as good as ChatGPT, with ChatGPT getting scores of 0.40 and 0.42. We also conduct a few experiments to demonstrate the robustness of our method, while also highlighting a few interesting caveats of the model.

  • Open Access

    Hierarchical Prompting Assists Large Language Model on Web Navigation

    by Robert Lo, Abishek Sridhar, Frank F. Xu, Hao Zhu, Shuyan Zhou

    Robert Lo, Abishek Sridhar, Frank Xu, Hao Zhu, Shuyan Zhou. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.