Papers by Parminder Bhatia

21 papers
ReCode: Robustness Evaluation of Code Generation Models (2023.acl-long)

Copied to clipboard

Challenge: Existing work on robustness in text or code tasks has focused on classification, while robustness for code generation tasks is an uncharted area.
Approach: They propose a robustness evaluation benchmark for code generation models that customizes over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format.
Outcome: The proposed model performs better on human annotators and on SOTA models with human annnotators.
Unity in Diversity: Collaborative Pre-training Across Multimodal Medical Sources (2024.acl-long)

Copied to clipboard

Challenge: Current pre-training techniques rely on a limited scope of medical data, limiting the range of downstream tasks.
Approach: They propose a pre-training strategy that unifies patient data within individual sources and captures explicit and implicit correlations between patients across different sources.
Outcome: The proposed strategy bridges the gap between multimodal medical sources by aggregating patient data within individual sources and capturing explicit and implicit correlations between patients across sources.
A Static Evaluation of Code Completion by Large Language Models (2023.acl-industry)

Copied to clipboard

Challenge: Large language models trained on code have shown great potential to increase productivity of software developers.
Approach: They propose a static evaluation framework to quantify static errors in Python code completions by leveraging Abstract Syntax Trees.
Outcome: The proposed framework is more efficient and applicable to code in the wild.
Severing the Edge Between Before and After: Neural Architectures for Temporal Ordering of Events (2020.emnlp-main)

Copied to clipboard

Challenge: Existing models for temporal ordering of events rely on pretrained representations, transfer and multitask learning, and self-training techniques.
Approach: They propose a neural architecture and a set of training methods for ordering events by predicting temporal relations by pre-training models.
Outcome: The proposed models can predict temporal relations between two pairs of events within a span of text and identify temporal relationships between them.
Relation Extraction using Explicit Context Conditioning (N19-1)

Copied to clipboard

Challenge: Existing methods for relation extraction fail to capture complex and long dependencies . end-to-end models that learn both NER and RE can solve this problem .
Approach: They propose to use second-order relations to compute relation scores for relation extraction (RE) . they propose to combine second- and first-order relation scores to obtain final relation scores .
Outcome: The proposed method leads to state-of-the-art performance over two biomedical datasets.
Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs (2025.naacl-long)

Copied to clipboard

Challenge: Prior work has shown that in-context learning (ICL) with retriever augmentation can help LLMs better capture long-tail knowledge, reducing their reliance on pre-trained data.
Approach: They propose a reinforcement learning-based dynamic uncertainty ranking method that accounts for the varying impact of each retrieved sample on LLM predictions.
Outcome: The proposed method outperforms baseline models on question-answering datasets by 2.76% and 5.96% on long-tail questions that elude zero-shot inference.
Towards Annotating and Creating Summary Highlights at Sub-sentence Level (D19-54)

Copied to clipboard

Challenge: Creating summary highlights at the sub-sentence level is desirable because sub-entrances are more concise than whole sentences.
Approach: They propose to annotate summary-worthy sub-sentences and teach classifiers to do the same . they frame task as selecting important sentences and identifying a single most informative textual unit from each sentence.
Outcome: The proposed method reduces the complexity involved in sentence compression by reducing the number of words and phrases deleted.
Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics (2021.findings-acl)

Copied to clipboard

Challenge: Current approaches to medical entity retrieval generalize poorly to unseen sub-specialties . zero-shot retrieval is challenging due to the high degree of ambiguity and variability in medical corpora .
Approach: They propose a set of learning tasks designed to train efficient zero-shot entity retrieval models.
Outcome: The proposed architecture outperforms common zero-shot benchmarks with 7% to 30% higher recall across multiple major medical ontologies.
Joint Entity Extraction and Assertion Detection for Clinical Text (P19-1)

Copied to clipboard

Challenge: Existing systems for in-formation extraction treat negative medical findings as a pipeline of two separate tasks.
Approach: They propose a multi-task neural model to jointly extract entities and negations from medical reports.
Outcome: The proposed model performs considerably better than existing systems on a 2010 i2b2/VA challenge dataset and a proprietary de-identified clinical dataset.
TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale (2024.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have advanced tasks like text summarization, but their size and computational demands limit their use in resource-constrained and privacy-centric settings.
Approach: They propose a framework for distilling LLMs’ text summarization abilities into a compact, local model using a curriculum learning strategy that evolves from simple to complex tasks.
Outcome: The proposed framework outperforms baseline models on CNN/DailyMail, XSum, and ClinicalTrial, and improves interpretability by providing insights into the summarization rationale.
An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training (2020.emnlp-main)

Copied to clipboard

Challenge: Pre-training large language models is a standard practice in the natural language processing community.
Approach: They propose to use elastic weight consolidation to mitigate catastrophic forgetting when pre-trained large language models are evaluated on generic benchmarks.
Outcome: The proposed model achieves state-of-the-art on out-of domain tasks with minimal pre-training . elastic weight consolidation provides best overall scores yielding only a 0.33% drop in performance across seven generic tasks while remaining competitive in bio-medical tasks.
Token Alignment via Character Matching for Subword Completion (2024.findings-acl)

Copied to clipboard

Challenge: Generative models struggle with prompts corresponding to partial tokens due to tokenization, where partial token is out-of-distribution during inference.
Approach: They propose a method to alleviate tokenization artifact on text completion by backtracking to the last complete tokens and aligning subsequent generations to match with the prompt.
Outcome: The proposed method shows that it improves on partial token scenarios with only a minor time increase.
Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning (2025.acl-long)

Copied to clipboard

Challenge: Existing methods rely on inference-time interventions, which are limited in attention adaptation or require additional supervision.
Approach: They propose a framework for automatic attention alignment tuning that leverages weak labels from SAM and selectively modifies visually-critical attention heads to improve alignment while minimizing interference.
Outcome: The proposed framework outperforms state-of-the-art models on medical VQA and report generation benchmarks.
Exploring Continual Learning for Code Generation Models (2023.acl-short)

Copied to clipboard

Challenge: Large-scale code generation models such as Copilot and CodeT5 are expensive to train and re-train.
Approach: They propose a benchmark for Continual Learning (CL) that covers a wide range of tasks with different input and output programming languages.
Outcome: The proposed method improves on Prompt Pooling with Teacher Forcing, which suffers catastrophic forgetting due to stark distribution shifts in coding tasks.
Multitask Pretraining with Structured Knowledge for Text-to-SQL Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for learning representations of structured knowledge are limited to the minority of people with technical skills.
Approach: They propose a large pretraining dataset and strategy for learning representations of text, tables, and SQL code that leverages the entire context of the problem.
Outcome: The proposed model improves on two SQL tasks and shows a 1.7 and 2.2 percentage point improvement over existing methods.
Neural Entity Recognition with Gazetteer based Fusion (2021.findings-acl)

Copied to clipboard

Challenge: Named entity recognition systems can be applied to clinical domains where only limited data is accessible and interpretability is important.
Approach: They propose to use auxiliary gazetteer model to fuse it with NER system . this allows for better robustness and interpretability across different clinical datasets .
Outcome: The proposed model is data efficient and can adapt to new mentions in gazetteers without retraining.
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization (2022.acl-short)

Copied to clipboard

Challenge: Empirical analyses show that pre-trained sequence-to-sequence models can achieve a 16.5x model footprint compression ratio with little performance drop relative to full-precision counterparts.
Approach: They propose to distill and quantize pre-trained sequence-to-sequence models to reduce memory and latency requirements.
Outcome: Empirical results show that the proposed model achieves 16.5x model footprint compression ratio with little performance drop relative to full-precision counterparts on multiple summarization and QA datasets.
ContraCLM: Contrastive Learning For Causal Language Model (2023.acl-long)

Copied to clipboard

Challenge: Existing studies show that causal language models lack expressiveness due to poor discrimination ability.
Approach: They propose a contrastive learning framework that enhances discrimination of representations and bridges the gap with encoder-only models.
Outcome: The proposed framework improves discrimination and source code generation capabilities on a variety of downstream tasks.
CoCoMIC: Code Completion by Jointly Modeling In-file and Cross-file Context (2024.lrec-main)

Copied to clipboard

Challenge: Pre-trained language models (LMs) for code have shown promising performance in code completion tasks but ignore the rich semantics in other files within the same project.
Approach: They propose a framework that jointly learns the in-file and cross-file context on top of code LMs and a static-analysis-based tool that locates and retrieves the most relevant project-level cross- file context for code completion.
Outcome: The proposed framework improves existing code LMs with a 33.94% relative increase in exact match and 28.69% in identifier matching when the cross-file context is provided.
BIPEFT: Budget-Guided Iterative Search for Parameter Efficient Fine-Tuning of Large Pretrained Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for parameter-efficient fine-tuning are limited by computational and storage requirements.
Approach: They propose a budget-guided iterative search strategy to disentangle binary module and rank dimension search spaces and early selection strategies based on parameter budgets.
Outcome: The proposed method significantly improves search efficiency on public benchmarks.
Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods for visual and language alignment depend on external models or data, leading to uncontrollable and unstable results.
Approach: They propose a framework that enhances visual and language alignment without external dependencies by incorporating an in-context self-critic mechanism that constructs preference pairs for tuning.
Outcome: The proposed framework outperforms existing methods and improves performance on 14 hallucination and comprehensive benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations