Papers by Suman Banerjee
AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection (2025.acl-long)
Copied to clipboard
| Challenge: | Existing defense agencies fail to adaptively and effectively mitigate these risks. |
| Approach: | They propose a lifelong agent guardrail that enhances LLM agent safety by enabling adaptive safety check generation, effective safety check optimization, and tool compatibility & flexibility. |
| Outcome: | The proposed agent guardrail achieves strong performance against task-specific and systemic risks and is transferable across different LLM agents’ tasks. |
Synthesize, if you do not have: Effective Synthetic Dataset Creation Strategies for Self-Supervised Opinion Summarization in E-commerce (2023.findings-emnlp)
Copied to clipboard
Tejpalsingh Siledar, Suman Banerjee, Amey Patil, Sudhanshu Singh, Muthusamy Chelliah, Nikesh Garera, Pushpak Bhattacharyya
| Challenge: | Existing approaches to generate general and aspect-specific opinion summarization are limited due to their reliance on human-specified aspects and seed words. |
| Approach: | They propose synthetic dataset creation approaches for general and aspect-specific opinion summarization . general opinion summaries struggle to generate faithful to the input reviews, they say . aspect- specific opinion summarisation models are limited due to reliance on human-specified aspects . |
| Outcome: | The proposed approach outperforms existing models on three e-commerce test sets on general and aspect-specific opinion summarization. |
One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation (2024.acl-long)
Copied to clipboard
Tejpalsingh Siledar, Swaroop Nath, Sankara Muddu, Rupasai Rangaraju, Swaprava Nath, Pushpak Bhattacharyya, Suman Banerjee, Amey Patil, Sudhanshu Singh, Muthusamy Chelliah, Nikesh Garera
| Challenge: | Existing evaluation methods for opinion summarizations lack adequate opinion summary evaluation datasets. |
| Approach: | They propose a dataset that combines 7 dimensions crucial to opinion summaries . they propose OP-I-PROMPT, a dimension-independent prompt, and OP PROMPTS, . |
| Outcome: | The proposed model achieves a Spearman correlation of 0.70 with human judgments, surpassing prior methods. |
A Dataset for Building Code-Mixed Goal Oriented Conversation Systems (C18-1)
Copied to clipboard
| Challenge: | Existing data on goal-oriented conversation systems focus on monolingual conversations and there is hardly any work on multilingual and/or code-mixed conversations. |
| Approach: | They build a goal-oriented dialog dataset containing code-mixed conversations using monolingual text from a restaurant reservation dataset. |
| Outcome: | The proposed model is based on a restaurant reservation dataset and will be made publicly available for research purposes. |
Towards Exploiting Background Knowledge for Building Conversation Systems (D18-1)
Copied to clipboard
| Challenge: | Existing dialog datasets contain a sequence of utterances without any explicit background knowledge associated with them. |
| Approach: | They propose to use movie chats to generate responses by copying unstructured background knowledge . they use a dataset of 9K conversations to test whether responses are generated by copy-and-modify models . |
| Outcome: | The proposed model mimics human process of conversing by copying and/or modifying sentences from unstructured background knowledge. |
Product Description and QA Assisted Self-Supervised Opinion Summarization (2024.findings-naacl)
Copied to clipboard
Tejpalsingh Siledar, Rupasai Rangaraju, Sankara Muddu, Suman Banerjee, Amey Patil, Sudhanshu Singh, Muthusamy Chelliah, Nikesh Garera, Swaprava Nath, Pushpak Bhattacharyya
| Challenge: | Existing methods to generate opinion summarization without supervised training data are limited due to the lack of additional sources. |
| Approach: | They propose a synthetic dataset creation strategy that leverages reviews and additional sources to generate a pseudo-summary. |
| Outcome: | The proposed approach achieves 14.5% improvement in ROUGE-1 F1 over existing models. |
Why We Feel What We Feel: Joint Detection of Emotions and Their Opinion Triggers in E-commerce (2025.findings-emnlp)
Copied to clipboard
Arnav Attri, Anuj Attri, Suman Banerjee, Amey Patil, Muthusamy Chelliah, Nikesh Garera, Pushpak Bhattacharyya
| Challenge: | Existing research has not explored the joint task of emotion detection and explanatory span identification in e-commerce reviews. |
| Approach: | They propose a joint task unifying Emotion detection and Opinion Trigger extraction (EOT) which explicitly models the relationship between causal text spans (opinion triggers) and affective dimensions (emotion categories). |
| Outcome: | The proposed framework surpasses zero-shot and chain-of-thought techniques across e-commerce domains. |