Papers by Amit Sharma

8 papers
Task Facet Learning: A Structured Approach To Prompt Optimization (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to prompt optimization are limited to learning multiple facets of a task from training examples.
Approach: They propose to optimize a text prompt by considering different facets of a task and including them in the prompt.
Outcome: The proposed algorithm can generate long, complex prompts that existing methods are unable to generate.
YinYang-Align: A new Benchmark for Competing Objectives and Introducing Multi-Objective Preference based Text-to-Image Alignment (2025.findings-acl)

Copied to clipboard

Challenge: Recent controversies highlight the need for robust alignment mechanisms in text-to-image systems.
Approach: They propose a framework to evaluate T2I systems across six contradictory alignment objectives . objectives highlight key trade-offs such as artistic freedom and cultural sensitivity .
Outcome: The proposed framework achieves superior alignment across all objectives.
Counter Turing Test (CT2): AI-Generated Text Detection is Not as Easy as You May Think - Introducing AI Detectability Index (ADI) (2023.emnlp-main)

Copied to clipboard

Challenge: a number of issues have arisen regarding the risk and consequences of AI-generated text detection.
Approach: They propose a counter-turing test to evaluate the robustness of existing AGTD methods . they propose ADI, a quantifiable spectrum to assess detectability of LLMs .
Outcome: The proposed method evaluates the robustness of existing AGTD methods . it shows that larger LLMs tend to have lower ADI, indicating they are less detectable .
HORIZON: A Benchmark for In-the-wild User Behaviour Modeling (2026.findings-acl)

Copied to clipboard

Challenge: Existing user modeling benchmarks focus on short sessions and next-item prediction within a single domain.
Approach: They propose a benchmark that reformulates user modeling along three axes . it covers 54M users and 35M items, enabling pretraining and evaluation . they propose tasks and evaluation setups that better reflect real-world deployment scenarios .
Outcome: The proposed benchmark covers 54M users and 35M items, and is based on Amazon Reviews.
Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers (2023.acl-long)

Copied to clipboard

Challenge: toxicity and IMDB review datasets show that pre-trained NLP classifiers learn spurious correlations between input features and label .
Approach: They propose an algorithm to regularize the learnt effect of features on the model’s prediction to the estimated effect of a feature on label.
Outcome: The proposed method minimises spurious correlations and improves minority group accuracy while improving total accuracy compared to standard training.
Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval (2025.emnlp-main)

Copied to clipboard

Challenge: Existing research does not explore key factors such as optimal augmentation scale and the necessity of using large augmentation models.
Approach: They propose to use LLMs to augment compact dual-encoder models to improve retrieval performance.
Outcome: The proposed approach improves retrieval performance but its benefits diminish beyond a certain scale even with diverse augmentation strategies.
NICE: To Optimize In-Context Examples or Not? (2024.acl-long)

Copied to clipboard

Challenge: Recent work shows that in-context learning and optimization of in-const examples (ICE) can improve the accuracy of large language models on a wide range of tasks.
Approach: They propose a task-specific metric called Normalized Invariability to Choice of Examples (NICE) metric measures the learnability of tasks from a given instruction and provides a heuristic to decide whether to optimize ICE for a new task.
Outcome: The proposed metric predicts the utility of optimizing ICE for a given task compared to random ICE.
Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi (2020.lrec-1)

Copied to clipboard

Challenge: 40% of all the languages in the world face the danger of extinction in the near future . when a language dies out, future generations lose a vital part of the culture that is necessary to completely understand it.
Approach: They propose to use 4 technology-driven methods of data collection to collect data on Gondi, a low-resource vulnerable language spoken by 2.3 million tribal people in south and central India.
Outcome: The proposed methods collected 12,000 translated words and/or sentences and identified more than 650 community members whose help can be solicited for future translation efforts.

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