Papers by Saurabh Agarwal
Regularized Graph Convolutional Networks for Short Text Classification (2020.coling-industry)
Copied to clipboard
| Challenge: | Short text classification is a problem in natural language processing, social network analysis, and e-commerce. |
| Approach: | They propose a short text classification technique that incorporates label dependencies into the output space to overcome the limitations of short text. |
| Outcome: | The proposed model outperforms baseline methods on proprietary and external datasets and is more robust to noise in textual features. |
Invariant Language Modeling (2022.emnlp-main)
Copied to clipboard
Maxime Peyrard, Sarvjeet Ghotra, Martin Josifoski, Vidhan Agarwal, Barun Patra, Dean Carignan, Emre Kiciman, Saurabh Tiwary, Robert West
| Challenge: | Existing methods to remove spurious correlations and biases involve expensive domain alignment. |
| Approach: | They propose a framework for learning invariant representations that generalize better across environments . they adapt a game-theoretic implementation of IRM to language models . |
| Outcome: | The proposed framework can remove structured noise, ignore correlations and achieve better generalization across environments. |
NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls (2025.emnlp-main)
Copied to clipboard
Kinjal Basu, Ibrahim Abdelaziz, Kiran Kate, Mayank Agarwal, Maxwell Crouse, Yara Rizk, Kelsey Bradford, Asim Munawar, Sadhana Kumaravel, Saurabh Goyal, Xin Wang, Luis A. Lastras, Pavan Kapanipathi
| Challenge: | Existing benchmarks and datasets for tool calling have lagged behind . nested sequencing is a common problem in LLMs, but it is not enough to evaluate them. |
| Approach: | They propose a benchmark to evaluate LLMs on nested sequences of API calls, i.e. sequences where the output of one API call is passed as input to a subsequent call. |
| Outcome: | The proposed model achieves a full sequence match accuracy of 28% and a win-rate of 60% on nested sequences of API calls. |
Decoding Speculative Decoding (2025.naacl-long)
Copied to clipboard
| Challenge: | Speculative decoding is a widely used technique to speed up inference for Large Language Models (LLMs) Autoregressive decoding has been known to be hardware inefficient, leading to poor resource utilization and low throughput during inference. |
| Approach: | They propose to use a draft model to generate speculative tokens and then use the target LLM to verify those tokens. |
| Outcome: | The proposed model can provide 111% higher throughput than existing draft models and generalizes further to all LLaMA models and supervised fine-tuned models. |
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding (2024.acl-long)
Copied to clipboard
Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich, Basil Hosmer, Bram Wasti, Liangzhen Lai, Anas Mahmoud, Bilge Acun, Saurabh Agarwal, Ahmed Roman, Ahmed Aly, Beidi Chen, Carole-Jean Wu
| Challenge: | Large Language Models (LLMs) have been deployed to many applications, yet their high compute and memory requirements lead to high financial and energy costs when deployed to GPU servers. |
| Approach: | They propose an end-to-end solution to speed-up inference of large language models . they apply layer dropout, and show that it increases the accuracy of early exit at earlier layers without adding any auxiliary layers or modules to the model. |
| Outcome: | The proposed method shows speedups of up to 2.16x on summarization for CNN/DM documents, 1.82x on coding, and 2.0x on TOPv2 semantic parsing task. |
Complex Question Answering on knowledge graphs using machine translation and multi-task learning (2021.eacl-main)
Copied to clipboard
Saurabh Srivastava, Mayur Patidar, Sudip Chowdhury, Puneet Agarwal, Indrajit Bhattacharya, Gautam Shroff
| Challenge: | Existing approaches to question answering on knowledge graphs are based on a modularized sequential approach where errors in one module lead to the accumulation of errors in downstream modules. |
| Approach: | They propose a multi-task BERT based Neural Machine Translation model to address these challenges. |
| Outcome: | The proposed model can answer questions over a knowledge graph on one publicly available and one proprietary dataset. |
Corpus for Automatic Structuring of Legal Documents (2022.lrec-1)
Copied to clipboard
Prathamesh Kalamkar, Aman Tiwari, Astha Agarwal, Saurabh Karn, Smita Gupta, Vivek Raghavan, Ashutosh Modi
| Challenge: | In populous countries, pending legal cases are growing exponentially. |
| Approach: | They propose a corpus of legal judgment documents in English that is annotated with a label coming from a list of pre-defined rhetorical roles. |
| Outcome: | The proposed corpus of legal judgment documents is annotated with a label coming from a list of pre-defined rhetorical roles. |
StitchLLM: Serving LLMs, One Block at a Time (2025.acl-long)
Copied to clipboard
Bodun Hu, Shuozhe Li, Saurabh Agarwal, Myungjin Lee, Akshay Jajoo, Jiamin Li, Le Xu, Geon-Woo Kim, Donghyun Kim, Hong Xu, Amy Zhang, Aditya Akella
| Challenge: | Existing techniques like distillation and pruning are not efficient for large language models. |
| Approach: | They propose a dynamic model routing framework that uses a powerful bottom model to process all queries and a lightweight routing mechanism to allocate computational resources appropriately. |
| Outcome: | The proposed framework improves system throughput while minimizing performance degradation. |