Papers by Sopan Khosla
Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods for unsupervised text style transfer focus on transferring a specific attribute, but this technique has never been explored in natural language generation tasks. |
| Approach: | They propose a counterfactual-based method to modify latent representations by posing a ‘what-if’ scenario. |
| Outcome: | The proposed method is tested on multiple attribute transfer tasks like Sentiment, Formality and Excitement to support the hypothesis. |
Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniques (2021.acl-long)
Copied to clipboard
| Challenge: | Creating digital SOAP notes is burdensome and contributes to physician burnout . authors propose a pipeline to generate these notes based on transcripts of clinical conversations . |
| Approach: | They propose a pipeline to leverage deep summarization models based on conversations between physicians and patients . they propose an algorithm that extracts important utterances relevant to each section and generates one summary sentence per cluster . |
| Outcome: | The proposed algorithm outperforms its abstract counterpart by 8 ROUGE-1 points and produces more factual sentences as assessed by human evaluators. |
The Universal Anaphora Scorer (2022.lrec-1)
Copied to clipboard
| Challenge: | a new version of the Reference Coreference Scorer is proposed to evaluate anaphoric interpretations . the proposed approach to evaluation of split antecedent anaphorisms is entirely novel . |
| Approach: | They propose an extended version of the Reference Coreference Scorer to evaluate anaphoric interpretations . the UA scorer supports the evaluation of split antecedent anaphorisms and discourse deixis . |
| Outcome: | The proposed method can be used to evaluate anaphoric interpretations in an extended range of anas . it supports evaluations of split antecedent anaphorisms and discourse deixis, for which no tools exist . |
Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA (2024.findings-naacl)
Copied to clipboard
| Challenge: | a universal question-answering system that can operate on any knowledge graph is presented . previous work that relied on training data to query structured data stores is unrealistic . |
| Approach: | They propose a universal question-answering system that can operate on any knowledge graph . they use an LLM-backed symbolic agent to generate query-program exemplars . |
| Outcome: | The proposed system outperforms state-of-the-art model on domain-specific KGs by 7.08 F1 . the proposed system can be ready to use within a day, the authors show . |
MedFilter: Improving Extraction of Task-relevant Utterances through Integration of Discourse Structure and Ontological Knowledge (2020.emnlp-main)
Copied to clipboard
| Challenge: | Identifying task-relevant utterances improves performance at downstream medical processing. |
| Approach: | They propose a novel approach that uses task-oriented conversations to improve utterance classification over SOTA models. |
| Outcome: | The proposed model improves on a corpus of 7,000 doctor-patient conversations on 7,000 patient conversations. |
Aff2Vec: Affect–Enriched Distributional Word Representations (C18-1)
Copied to clipboard
| Challenge: | Affective word distributions are not well understood in literature. |
| Approach: | They propose a model that embeds affective word interpretations into enriched word embeddings. |
| Outcome: | The proposed model outperforms the state-of-the-art in word-similarity tasks and in emotion analysis, personality detection, and frustration prediction tasks. |
Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work on entity coreference resolution (CR) follows current trends in Deep Learning . traditional approaches do not make use of hierarchical representations of discourse structure . |
| Approach: | They propose to leverage automatically constructed discourse parse trees within a neural approach to generate anaphoric mentions. |
| Outcome: | The proposed model improves on two benchmark entity coreference-resolution datasets. |
FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance (2025.emnlp-main)
Copied to clipboard
Mintong Kang, Vinayshekhar Bannihatti Kumar, Shamik Roy, Abhishek Kumar, Sopan Khosla, Balakrishnan Murali Narayanaswamy, Rashmi Gangadharaiah
| Challenge: | Text-to-image diffusion models often exhibit generation biases toward specific demographic groups, raising ethical concerns and limiting their adoption. |
| Approach: | They propose an adaptive latent guidance mechanism which controls the generation distribution during inference by dynamically adjusting the diffusion process to enforce specific attributes. |
| Outcome: | The proposed model outperforms existing models on HBE and Stable Bias datasets and achieves substantial bias reduction. |
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following (2026.acl-long)
Copied to clipboard
Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Kumar Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Hassan Awadalla, Manaal Faruqui
| Challenge: | Recent advances in large language models (LLMs) have shown impressive performance on a range of tasks, yet advanced instruction following (IF) remains a significant challenge. |
| Approach: | They propose a benchmark that features over 1,600 prompts and expert-curated rubrics that assess LLMs’ ability to follow complex, multi-turn, and system-level instructions. |
| Outcome: | The proposed framework improves instruction-following abilities of large language models, achieving a 6.7% gain on AdvancedIF and strong results on public benchmarks. |
Benchmarking the Covariate Shift Robustness of Open-world Intent Classification Approaches (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing benchmarks for open-world intent classification focus on the second aspect of the problem. |
| Approach: | They propose two datasets that include utterances useful for evaluating the robustness of open-world models to covariate shift. |
| Outcome: | The proposed datasets provide a more realistic evaluation scenario for open-world intent classification in task-oriented dialog systems. |