Papers by Sahana Ramnath
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning (2023.emnlp-main)
Copied to clipboard
Ximing Lu, Faeze Brahman, Peter West, Jaehun Jung, Khyathi Chandu, Abhilasha Ravichander, Prithviraj Ammanabrolu, Liwei Jiang, Sahana Ramnath, Nouha Dziri, Jillian Fisher, Bill Lin, Skyler Hallinan, Lianhui Qin, Xiang Ren, Sean Welleck, Yejin Choi
| Challenge: | Extreme-scale language models have shown exceptional performance on a variety of language tasks, but the degree of control offered by these models through pure prompting is limited. |
| Approach: | They propose an inference-time policy adapter which tailors a large base model without fine-tuning it. |
| Outcome: | The proposed model outperforms baseline methods on five challenging text generation tasks and even over GPT-4. |
Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-text Rationales (2023.acl-long)
Copied to clipboard
Brihi Joshi, Ziyi Liu, Sahana Ramnath, Aaron Chan, Zhewei Tong, Shaoliang Nie, Qifan Wang, Yejin Choi, Xiang Ren
| Challenge: | Existing metrics like task performance of the LM generating the rationales or similarity between generated and gold rationale are not good indicators of their human utility. |
| Approach: | They propose to use a large language model to generate rationales with better human utility by estimating its conciseness and novelty. |
| Outcome: | The proposed model can measure human utility to a better extent by estimating its usefulness in answering similar unseen instances. |
Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries (2025.emnlp-main)
Copied to clipboard
| Challenge: | a typical human-assistant conversation is lengthy and shows significant diversity in topics, intents, and requirements across turns. |
| Approach: | They propose a framework that leverages pertinent linguistic concepts of dialog-acts and maxims to improve the accuracy of LLM-judges on preference data with complex, multi-turn conversational context. |
| Outcome: | The proposed framework improves on 4 challenging datasets showing that humans frequently change their intents from one turn of the conversation to the next. |
CAVE: Controllable Authorship Verification Explanations (2025.naacl-long)
Copied to clipboard
| Challenge: | Authorship Verification (AV) is used for tasks such as plagiarism detection, forensic analysis, analysis of the spread of misinformation. |
| Approach: | They propose to train an offline authorship verification model that is accessible and easy to use. |
| Outcome: | The proposed model generates high quality explanations and competitive task accuracy on three difficult AV datasets. |
ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations (2025.findings-acl)
Copied to clipboard
Brihi Joshi, Keyu He, Sahana Ramnath, Sadra Sabouri, Kaitlyn Zhou, Souti Chattopadhyay, Swabha Swayamdipta, Xiang Ren
| Challenge: | Language models are widely used in education, yet their ability to tailor responses to learners with varied informational needs and knowledge backgrounds remains under-explored. |
| Approach: | They conduct two extensive human studies to assess the utility of language model-generated explanatory answers (explanations) on a benchmark of 13.4K "Why" questions. |
| Outcome: | The proposed model explanations match learners' educational backgrounds only 50% of the time, compared to 79% for lay explanations. |
HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints (2021.emnlp-main)
Copied to clipboard
| Challenge: | HintedBT provides hints (as source tags on the encoder) about the quality of each source-target pair. |
| Approach: | They propose a method which provides hints to the encoder and decoder to improve the quality of BT data by providing hints about the quality. |
| Outcome: | The proposed method improves translation quality and performance in three low/medium-resource language pairs. |
Towards Interpreting BERT for Reading Comprehension Based QA (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained language models such as ELMO and XLNet have achieved state-of-the-art performance on various NLP tasks. |
| Approach: | They propose to define a layer’s role or functionality using Integrated Gradients and perform preliminary analysis across all layers. |
| Outcome: | The proposed model performs better than existing models on RCQA and ELMO, but it lacks the human-level performance needed to perform the task. |