Papers by Biswesh Mohapatra
Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior studies have demonstrated that Large Language Models (LLMs) are capable of performing grounding acts such as requesting clarification or producing acknowledgments, yet relatively little work has investigated how common ground can be explicitly represented and stored for later use. |
| Approach: | They propose to use relational references to represent common ground in situated dialogues and propose to improve both the establishment of common ground and its subsequent use in the conversation. |
| Outcome: | The proposed models can establish and exploit common ground in situated dialogues and improve its subsequent use. |
Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Popular dialog datasets such as MultiWOZ are created by providing crowd workers with instructions that describe the task to be accomplished. |
| Approach: | They propose a data creation strategy that uses a pre-trained language model to simulate the interaction between crowd workers by creating a user bot and an agent bot. |
| Outcome: | The proposed data creation strategy improves on two publicly available datasets using a pre-trained language model and a smaller percentage of actual crowd-generated conversations and their corresponding instructions. |
Evaluating the Effectiveness of Large Language Models in Establishing Conversational Grounding (2024.emnlp-main)
Copied to clipboard
| Challenge: | despite its importance, there has been limited research on conversational grounding in recent years . pre-trained language models have been costly and time-consuming to evaluate . |
| Approach: | They evaluate the performance of large language models in various aspects of conversational grounding . they propose ways to enhance the capabilities of the models that lag in this aspect . |
| Outcome: | The proposed model performance is based on pre-trained language models and a large pre-training dataset. |
Conversational Grounding: Annotation and Analysis of Grounding Acts and Grounding Units (2024.lrec-main)
Copied to clipboard
| Challenge: | Successful conversations often rest on common understanding, says a researcher . despite recent advances in dialog systems, there is a noticeable deficit in their grounding capabilities . |
| Approach: | They propose to use a framework to build conversational grounding in dialogs . they propose to analyze two dialog corpora using grounding acts and grounding units . |
| Outcome: | The proposed model shows that language models are not enough to ground dialogs with machines . the proposed model can be used to test the performance of existing Language Models . |