Papers by Rahul Khanna
LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation (2020.acl-demos)
Copied to clipboard
Dong-Ho Lee, Rahul Khanna, Bill Yuchen Lin, Seyeon Lee, Qinyuan Ye, Elizabeth Boschee, Leonardo Neves, Xiang Ren
| Challenge: | Existing frameworks for sequence labeling and classification require massive human effort and labeling data is limited. |
| Approach: | They propose a web-based, Label-Efficient AnnotatioN framework that allows an annotator to provide the needed labels for a task and can capture explanations for each labeling decision. |
| Outcome: | The proposed framework surpasses baseline F1 scores by 5-10 percentage points while using 2X times fewer labeled instances. |
Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations (2025.emnlp-main)
Copied to clipboard
Abhilekh Borah, Chhavi Sharma, Danush Khanna, Utkarsh Bhatt, Gurpreet Singh, Hasnat Md Abdullah, Raghav Kaushik Ravi, Vinija Jain, Jyoti Patel, Shubham Singh, Vasu Sharma, Arpita Vats, Rahul Raja, Aman Chadha, Amitava Das
| Challenge: | a new metric measures the quality of large language models (LLMs) that detects hidden misalignments and jailbreak risks. |
| Approach: | They propose a decoding-invariant metric that measures latent safety failures . they propose 'Alignment Quality Index' to measure latent activations in latent space . |
| Outcome: | The proposed metric detects latent safety failures overlooked by behavioral benchmarks and jailbreaks. |
Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-Trained Language Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that pre-trained language models possess certain commonsense and factual knowledge. |
| Approach: | They propose to use pre-trained language models to predict masked words . they introduce a probing task with 13.6k m-word-prediction probes . |
| Outcome: | The proposed model performs poorly on the diagnostic dataset prior to any fine-tuning and fine-testing with distant supervision. |
RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have impressive performance on commonsense inference benchmarks, but their ability to make robust inferences is debated. |
| Approach: | They propose a challenge that evaluates robust commonsense inference despite textual perturbations using commonsensical knowledge bases and probe PTLMs across two different evaluation settings. |
| Outcome: | The proposed procedure evaluates robust commonsense inference despite textual perturbations using commonsensense knowledge bases and probe PTLMs across two evaluation settings. |
ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data (2021.acl-long)
Copied to clipboard
| Challenge: | Existing automated forecasting studies rely on structured data to predict future events. |
| Approach: | They propose a question-answering task that limits access to unstructured text data . they use a crowdsourced dataset to form a restricted-domain, multiple-choice, question-announcement task . |
| Outcome: | The proposed model achieves 61.0% accuracy on the dataset, which still lags behind human performance by about 19%. |