Papers by Abhishek Kumar
Wanda++: Pruning Large Language Models via Regional Gradients (2025.findings-acl)
Copied to clipboard
Yifan Yang, Kai Zhen, Bhavana Ganesh, Aram Galstyan, Goeric Huybrechts, Markus Müller, Jonas M. Kübler, Rupak Vignesh Swaminathan, Athanasios Mouchtaris, Sravan Babu Bodapati, Nathan Susanj, Zheng Zhang, Jack FitzGerald, Abhishek Kumar
| Challenge: | Existing pruning methods suffer from accuracy degradation without full-model sparsity-aware fine-tuning. |
| Approach: | They propose a pruning framework that uses decoder-block-level regional gradients to improve pruning accuracy. |
| Outcome: | The proposed pruning framework outperforms the state-of-the-art pruning frameworks by utilizing decoder-block-level regional gradients. |
Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding (2026.acl-long)
Copied to clipboard
Yuhang Zhou, Mingrui Zhang, Ke Li, Mingyi Wang, Qiao Liu, Qifei Wang, Jiayi Liu, Fei Liu, Serena Li, Weiwei LI, Mingze Gao, Abhishek Kumar, Xiangjun Fan, Zhuokai Zhao, Lizhu Zhang
| Challenge: | Large language models (LLMs) have shown promise on understanding and reasoning over tables, but current approaches remain limited. |
| Approach: | They propose a multi-agent framework that decomposes table reasoning into three specialized roles: planning, coding, and answering. |
| Outcome: | The proposed framework decomposes table reasoning into three specialized roles: planning, coding, and answering. |
Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization (2024.findings-acl)
Copied to clipboard
Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li, Zifeng Wang, Long Le, Abhishek Kumar, James Glass, Alexander Ratner, Chen-Yu Lee, Ranjay Krishna, Tomas Pfister
| Challenge: | Large language models struggle to capture relevant information located in the middle of their input. |
| Approach: | They propose a calibration mechanism that allows the model to attend to contexts faithfully according to their relevance even when they are in the middle. |
| Outcome: | The proposed calibration mechanism mitigates this positional bias and improves retrieval-augmented generation performance. |
Neural Conversational QA: Learning to Reason vs Exploiting Patterns (2020.emnlp-main)
Copied to clipboard
| Challenge: | Neural Conversational QA tasks such as ShARC require systems to answer questions based on the contents of a given passage. |
| Approach: | They propose to modify a data-set with fewer spurious patterns to exploit them . they also propose to build a heuristic-based program to exploit spurious clues . |
| Outcome: | The proposed program exploits spurious patterns in the ShARC dataset, compared to neural models. |
Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly used in high-stakes areas such as healthcare, law, and education. |
| Approach: | They propose a concept of Confidence-Probability Alignment that connects an LLM’s internal confidence to the confidence conveyed in the model’s response when explicitly asked about its certainty. |
| Outcome: | The proposed model shows the strongest confidence-probability alignment across a wide range of tasks. |
Knowledge-Enriched Two-Layered Attention Network for Sentiment Analysis (N18-2)
Copied to clipboard
| Challenge: | Existing sentiment analysis systems are prone to word shortening, exaggeration, lack of grammar and appropriate punctuation. |
| Approach: | They propose a two-layered attention network based on Bidirectional Long Short-Term Memory for sentiment analysis using the Knowledge Graph Embedding generated using the WordNet. |
| Outcome: | The proposed model outperforms the state-of-the-art system on the benchmark dataset of SemEval 2017 Task 5 by 1.7 and 3.7 points respectively. |
MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines (2020.lrec-1)
Copied to clipboard
Mihail Eric, Rahul Goel, Shachi Paul, Abhishek Sethi, Sanchit Agarwal, Shuyang Gao, Adarsh Kumar, Anuj Goyal, Peter Ku, Dilek Hakkani-Tur
| Challenge: | MultiWOZ 2.0 has substantial noise in dialogue state annotations and dialogue utterances . follow-up work has augmented the original dataset with user dialogue acts . |
| Approach: | They propose to reannotate dialogue state and utterances based on original dataset . they then compare their results to other datasets to improve their models . |
| Outcome: | The proposed dataset improves on the noise in the dialogue state annotations and dialogue utterances. |
Reasoning with Memory: Adaptive Information Management for Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Multi-hop reasoning remains a fundamental challenge for Retrieval-Augmented Generation systems. |
| Approach: | They propose a framework that provides a dynamic cognitive workspace for multi-hop reasoning . it uses an explicit working memory that persists across retrieval cycles and is continuously updated . |
| Outcome: | The proposed framework achieves state-of-the-art performance over existing systems on eight QA benchmarks. |
FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance (2025.emnlp-main)
Copied to clipboard
Mintong Kang, Vinayshekhar Bannihatti Kumar, Shamik Roy, Abhishek Kumar, Sopan Khosla, Balakrishnan Murali Narayanaswamy, Rashmi Gangadharaiah
| Challenge: | Text-to-image diffusion models often exhibit generation biases toward specific demographic groups, raising ethical concerns and limiting their adoption. |
| Approach: | They propose an adaptive latent guidance mechanism which controls the generation distribution during inference by dynamically adjusting the diffusion process to enforce specific attributes. |
| Outcome: | The proposed model outperforms existing models on HBE and Stable Bias datasets and achieves substantial bias reduction. |
Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Representative bias is a tendency of Large Language Models to generate outputs that mirror the experiences of certain identity groups, and affinity bias is an evaluative preference for specific narratives. |
| Approach: | They propose two new metrics to measure representative bias and affinity bias within large language models and present a new set of tasks designed with customized rubrics to detect these biases. |
| Outcome: | The proposed model identifies representative biases in prominent LLMs, with a preference for identities associated with being white, straight, and men. |