Papers by Abhishek Kumar

10 papers
Wanda++: Pruning Large Language Models via Regional Gradients (2025.findings-acl)

Copied to clipboard

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

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

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

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

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.

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