Papers by Apoorv Saxena
Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition (2024.emnlp-main)
Copied to clipboard
| Challenge: | Prior research addresses generating attributions alongside responses in open domains, either per sentence or per paragraph. |
| Approach: | They propose a method to decompose generated answers for attribution using template-based in-context learning. |
| Outcome: | The proposed approach enhances the semantic understanding of abstractive and extractive answers. |
Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Long document question answering requires locating relevant paragraphs within a document to answer a question. |
| Approach: | They propose to exploit the discourse structure commonly found in documents to create a condensed representation of the document, enabling a more comprehensive understanding and analysis of relationships between different parts. |
| Outcome: | The proposed approach retains 99.6% of the best zero-shot approach's performance while processing only 26% of tokens used by the best approach in the information seeking evidence retrieval setup. |
TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent years have witnessed interest in Temporal Question Answering over Knowledge Graphs (TKGQA) but these methods are highly engineered and do not automatically discover relevant parts of the KG during multi-hop reasoning. |
| Approach: | They propose a scheme to modulate the messages passed through a KG edge during convolution based on the relevance of its associated period to the question. |
| Outcome: | The proposed system outperforms state-of-the-art models on a recent challenging dataset for multi-hop complex temporal QA called TimeQuestions. |
Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs (2025.naacl-long)
Copied to clipboard
Anirudh Phukan, Divyansh Divyansh, Harshit Kumar Morj, Vaishnavi Vaishnavi, Apoorv Saxena, Koustava Goswami
| Challenge: | Large Multimodal Models are plagued by hallucinations that limit their reliability and adoption. |
| Approach: | They propose a method that leverages contextual token embeddings from LMMs to detect hallucinations. |
| Outcome: | The proposed method improves hallucination detection and grounding across diverse categories while excelling in tasks requiring contextual understanding. |
Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models have demonstrated strong capabilities in transforming text descriptions or tables to data visualizations . however, it is not straightforward to apply these methods directly for a more real-world use case of visualizing data from long documents . |
| Approach: | They propose an unsupervised method for generating intent-based charts from documents . they propose an attribution-based metric that uses a structured textual representation of charts . |
| Outcome: | The proposed method outperforms baselines in terms of chart data accuracy and chart type over baselines. |
Sequence-to-Sequence Knowledge Graph Completion and Question Answering (2022.acl-long)
Copied to clipboard
| Challenge: | Knowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embeddable vectors. |
| Approach: | They propose to use an off-the-shelf encoder-decoder Transformer model to generate a knowledge graph embedding model that can be used for KG link prediction and incomplete KG question answering. |
| Outcome: | The proposed model outperforms baselines on multiple large-scale datasets without extensive hyperparameter tuning. |
Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly used for question answering . lack of explicit references or attributions hinders ability to verify accuracy of answers . |
| Approach: | They propose a method for attribution in contextual question answering . they use hidden state representations of large language models to identify copied segments . |
| Outcome: | The proposed method performs better than GPT-4 at identifying verbatim copied segments in LLM generations and attributing these segments to their source. |
Open-World Factually Consistent Question Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for question generation suffer from factual inconsistencies and incorrect entities and are not answerable from the input paragraph. |
| Approach: | They propose a data processing technique based on de-lexicalization for consistent question generation across domains and a model that is generic across question-generation models. |
| Outcome: | The proposed method produces entity-level factually consistent questions without significant impact on traditional metrics. |
PLD+: Accelerating LLM Inference by Leveraging Language Model Artifacts (2025.findings-naacl)
Copied to clipboard
| Challenge: | speculative decoding is a novel decoding paradigm for large language models . however, its use is limited by its computational resources and fine-tuning requirements . |
| Approach: | They propose a tuning-free approach that accelerates inference of large language models . they use draft and verify principle to accelerate inference process . |
| Outcome: | The proposed approach outperforms tuning-free approaches on input-guided tasks and outperformed state-of-the-art EAGLE on four of the tasks. |
A Tale of Two Revisions: Summarizing Changes Across Document Versions (2024.findings-acl)
Copied to clipboard
| Challenge: | Document revision is a crucial aspect of the writing process, especially in collaborative environments where multiple authors contribute simultaneously. |
| Approach: | They propose a task of providing thematic summary of changes between document versions, organizing individual edits based on shared themes, and propose three strategies to tackle this task. |
| Outcome: | The proposed model improves its capacity to handle the task and also enables it to be used in a curated dataset. |
Question Answering Over Temporal Knowledge Graphs (2021.acl-long)
Copied to clipboard
| Challenge: | Temporal Knowledge Graphs (Temporal KGs) provide temporal scopes (start and end times) on each edge in the Knowledge . Lack of broad coverage datasets has been limiting progress in this area . |
| Approach: | They propose a transformer-based solution that exploits recent advances in Temporal Knowledge Graph embeddings and achieves an increase of 120% in accuracy over the next best performing method. |
| Outcome: | The proposed solution improves on the only known dataset by 340x . it increases accuracy by 120% over the baseline solution . |
Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings (2020.acl-main)
Copied to clipboard
| Challenge: | Existing multi-hop KGQA methods impose heuristic neighborhood limits, which often make it much harder to answer the input NL question. |
| Approach: | They propose to use knowledge Graphs (KG) to answer natural language queries over the KG. |
| Outcome: | The proposed method is particularly effective in performing multi-hop KGQA over sparse KGs. |
Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG (2026.findings-acl)
Copied to clipboard
| Challenge: | Query enhancement techniques are now standard in retrieval-augmented generation systems, yet their impact on these biases remains unexplored. |
| Approach: | They evaluate query enhancement techniques that improve retrieval quality . they find that simple rewriting reduces bias through increased score variance . no technique uniformly addresses all biases, and effects vary substantially across retrievers . |
| Outcome: | The proposed method achieves strongest aggregate reduction, but fails under adversarial conditions where multiple biases combine. |
RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis (2026.findings-eacl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) provide no visibility into which parts of visual data informed their conclusions. |
| Approach: | They propose a semi-automatic approach to attribute reasoning process by highlighting regions in charts and graphs that justify model answers. |
| Outcome: | The proposed method improves attribution accuracy by up to 15 percentage points compared to baseline methods and achieves high semantic similarity with ground truth responses. |