Papers by Rajarshi Das
When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories (2023.acl-long)
Copied to clipboard
| Challenge: | Large language models struggle with tasks requiring rich world knowledge, implying the difficulty of encoding a wealth of world knowledge in their parameters. |
| Approach: | They propose a retrieval-augmentation method that improves performance and reduces inference costs by only retrieving non-parametric memories when necessary. |
| Outcome: | The proposed method improves performance and reduces inference costs by only retrieving non-parametric memories when necessary. |
Optimal Transport-based Alignment of Learned Character Representations for String Similarity (P19-1)
Copied to clipboard
| Challenge: | String similarity models are crucial for record linkage, data integration, search and entity resolution systems. |
| Approach: | They propose a model that encodes the characters of each string, aligns the encodings using Sinkhorn Iteration and scores the alignment with a convolutional neural network. |
| Outcome: | The proposed model outperforms state-of-the-art and classical similarity models on four of the five datasets and improves performance by applying it to cross-document coreference. |
Constrained Decoding with Speculative Lookaheads (2025.naacl-long)
Copied to clipboard
Nishanth Sridhar Nakshatri, Shamik Roy, Rajarshi Das, Suthee Chaidaroon, Leonid Boytsov, Rashmi Gangadharaiah
| Challenge: | Constrained decoding with lookahead heuristics is effective for aligning LLM generations to human preferences, but the extensive lookaheaded roll-out operations for each generated token make it prohibitively expensive. |
| Approach: | They propose a technique that uses lookaheads to align LLMs to human preferences . they propose 2.2x to 12.15x speedup over greedy decoding . |
| Outcome: | The proposed technique achieves 2.2x to 12.15x speedup over greedy decoding without significant performance reduction. |
Do Multi-hop Readers Dream of Reasoning Chains? (D19-58)
Copied to clipboard
| Challenge: | Existing models for multihop reasoning are limited in their performance . multi-hop reasoning requires the ability to gather information from multiple passages . |
| Approach: | They propose a method that provides the full reasoning chain of multiple passages instead of just one final passage where the answer appears. |
| Outcome: | The proposed model improves on existing models by providing the full reasoning chain of multiple passages instead of just one final passage where the answer appears. |
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization (2025.findings-acl)
Copied to clipboard
Amitava Das, Suranjana Trivedy, Danush Khanna, Yaswanth Narsupalli, Basab Ghosh, Rajarshi Roy, Gurpreet Singh, Vinija Jain, Vasu Sharma, Aishwarya Naresh Reganti, Aman Chadha
| Challenge: | Direct Preference Optimization (DPO) is a cornerstone for preference alignment but is constrained by fixed divergence measures and limited feature transformations. |
| Approach: | They propose a new enhancement of Direct Preference Optimization that integrates kernel methods to overcome these challenges. |
| Outcome: | The proposed model improves divergence measures and features by using kernels . the proposed model achieves state-of-the-art generalization in factuality, safety, reasoning, and instruction following . |
DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions (2022.naacl-main)
Copied to clipboard
Neha Kennard, Tim O’Gorman, Rajarshi Das, Akshay Sharma, Chhandak Bagchi, Matthew Clinton, Pranay Kumar Yelugam, Hamed Zamani, Andrew McCallum
| Challenge: | Prior work on labeling arguments extracted from peer review text has focused qualified labor force on labelling arguments extracted by the text. |
| Approach: | They synthesize label sets from prior work and extend them to include fine-grained annotations of review and rebuttal sentences. |
| Outcome: | The proposed dataset synthesizes label sets from prior work and extends them to include fine-grained annotation of review and rebuttal sentences. |
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 . |
Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering (D19-58)
Copied to clipboard
Rajarshi Das, Ameya Godbole, Dilip Kavarthapu, Zhiyu Gong, Abhishek Singhal, Mo Yu, Xiaoxiao Guo, Tian Gao, Hamed Zamani, Manzil Zaheer, Andrew McCallum
| Challenge: | Multi-hop question answering (QA) requires an information retrieval system that can find multiple supporting evidence needed to answer the question. |
| Approach: | They propose a technique that uses information of entities present in the initial retrieved evidence to learn to ‘hop’ onto other relevant evidence. |
| Outcome: | The proposed method boosts retrieval performance on a multi-hop question answering dataset with 5 million Wikipedia paragraphs and a model without training increases its performance by 10.59 F1. |
Long Document Summarization in a Low Resource Setting using Pretrained Language Models (2021.acl-srw)
Copied to clipboard
Ahsaas Bajaj, Pavitra Dangati, Kalpesh Krishna, Pradhiksha Ashok Kumar, Rheeya Uppaal, Bradford Windsor, Eliot Brenner, Dominic Dotterrer, Rajarshi Das, Andrew McCallum
| Challenge: | Existing abstractive summarization methods only achieve 17.9 ROUGE-L in low-resource settings. |
| Approach: | They propose to use a modern abstractive summarization algorithm to extract salient sentences from long documents to improve their performance. |
| Outcome: | The proposed method beats several competitive salience detection baselines and the identified salient sentences agree with independent human labeling by domain experts. |
An Interface for Annotating Science Questions (D18-2)
Copied to clipboard
Michael Boratko, Harshit Padigela, Divyendra Mikkilineni, Pritish Yuvraj, Rajarshi Das, Andrew McCallum, Maria Chang, Achille Fokoue, Pavan Kapanipathi, Nicholas Mattei, Ryan Musa, Kartik Talamadupula, Michael Witbrock
| Challenge: | a new interface for human annotation of science question-answer pairs with their knowledge and reasoning types is proposed . the interface is based on previous work on the ARC dataset, but does not provide clear definitions of these types of knowledge. |
| Approach: | They propose an interface for human annotation of science question-answer pairs with their respective knowledge and reasoning types. |
| Outcome: | The proposed interface improves the classification of science questions in a preliminary study involving 10 participants. |
Case-based Reasoning for Natural Language Queries over Knowledge Bases (2021.emnlp-main)
Copied to clipboard
Rajarshi Das, Manzil Zaheer, Dung Thai, Ameya Godbole, Ethan Perez, Jay Yoon Lee, Lizhen Tan, Lazaros Polymenakos, Andrew McCallum
| Challenge: | Using human-labeled examples, case-based reasoning can solve complex problems from scratch . case-Based reasoning is a paradigm that is used to solve complex problem . |
| Approach: | They propose a neuro-symbolic CBR approach for question answering over large knowledge bases. |
| Outcome: | The proposed approach outperforms the current state of the art on a CWQ dataset by 11% on accuracy. |
An Instance Level Approach for Shallow Semantic Parsing in Scientific Procedural Text (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to parse scientific text using grammatically similar labeled sentences are limited and expensive to create. |
| Approach: | They propose a method where semantic labels from structurally similar sentences are copied to test sentences. |
| Outcome: | The proposed approach outperforms baseline and prior methods by 0.75 to 3 F1 absolute in the wet lab protocol corpus and 1 F1 absolut in the materials science procedural text corpus. |
ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing question answering datasets for common sense reasoning are lacking for prototypical situations. |
| Approach: | They propose a question answering dataset for training and evaluating common sense reasoning capabilities of artificial intelligence systems in such prototypical situations. |
| Outcome: | The proposed model outperforms existing models on all evaluation metrics with a meaningful gap. |
Machine Reading Comprehension using Case-based Reasoning (2023.findings-emnlp)
Copied to clipboard
Dung Thai, Dhruv Agarwal, Mudit Chaudhary, Wenlong Zhao, Rajarshi Das, Jay-Yoon Lee, Hannaneh Hajishirzi, Manzil Zaheer, Andrew McCallum
| Challenge: | Current state-of-the-art machine readers do not support case-based reasoning . |
| Approach: | They propose a method that extracts a set of similar cases from a nonparametric memory and then predicts an answer by selecting the span in the test context that is most similar to the contextualized representations of answers. |
| Outcome: | The proposed method outperforms baselines on NaturalQuestions and NewsQA by 11.5 and 8.4 EM. |
Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for learning non-parametric representations of entities and relations are based on tensor factorization or sophisticated neural approaches. |
| Approach: | They propose a case-based reasoning system that retrieves ‘cases’ that are similar to the given problem and then stores them in its parameters. |
| Outcome: | The proposed model outperforms state-of-the-art methods on several benchmark datasets and is non-parametric and grows dynamically as new entities and relations arrive in the KB. |
Chains-of-Reasoning at TextGraphs 2019 Shared Task: Reasoning over Chains of Facts for Explainable Multi-hop Inference (D19-53)
Copied to clipboard
| Challenge: | EMNLP 2019 shared task on 'Multi-hop Inference Explanation Regeneration' identifies chains of facts relevant to explain an answer to an elementary science examination question. |
| Approach: | They propose a system that identifies chains of facts relevant to explain an answer to an elementary science examination question. |
| Outcome: | The proposed system outperforms the second best system by 14.95 points on the mean average precision (MAP) metric. |
Calibration of Machine Reading Systems at Scale (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to calibrate open setting machine reading systems fail to scale to these settings due to various scale limitations in practical settings. |
| Approach: | They propose to extend existing calibration approaches to calibrate open-domain question answering and claim verification systems to these settings. |
| Outcome: | The proposed calibration methods can selectively predict answers when question answering systems are posed with unanswerable or out-of-the-training distribution questions. |