Search Results for author:
Found 14 papers, 5 papers with code
Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs
The rapid development of Large Multimodal Models (LMMs) has significantly advanced multimodal understanding by harnessing the language abilities of Large Language Models (LLMs) and integrating modality-specific encoders.
Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition
In this paper, we propose and investigate a novel approach to the factual decomposition of generated answers for attribution, employing template-based in-context learning.
Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approach
Generating presentation slides from a long document with multimodal elements such as text and images is an important task.
Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering
Attributing model generations to the input source document is essential to ensure trustworthiness and reliability.
Towards Optimizing the Costs of LLM Usage
In this work, we propose optimizing the usage costs of LLMs by estimating their output quality (without actually invoking the LLMs), and then solving an optimization routine for the LLM selection to either keep costs under a budget, or minimize the costs, in a quality and latency aware manner.
Social Media Ready Caption Generation for Brands
Our architecture is based on two parts: a the first part contains an image captioning model that takes in an image that the brand wants to post online and gives a plain English caption; b the second part takes in the generated caption along with the target brand personality and outputs a catchy personality-aligned social media caption.
Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering
We address the task of evidence retrieval for long document question answering, which involves locating relevant paragraphs within a document to answer a question.
A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis
First, our attention segregation loss reduces the cross-attention overlap between attention maps of different concepts in the text prompt, thereby reducing the confusion/conflict among various concepts and the eventual capture of all concepts in the generated output.
Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction
We propose KGT5-context, a simple sequence-to-sequence model for link prediction (LP) in knowledge graphs (KG).
Ranked #2 on
Link Prediction
on Wikidata5M
TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs
Recent years have witnessed much interest in temporal reasoning over knowledge graphs (KG) for complex question answering (QA), but there remains a substantial gap in human capabilities.
Ranked #3 on
Question Answering
on TimeQuestions
Sequence-to-Sequence Knowledge Graph Completion and Question Answering
These methods have recently been applied to KG link prediction and question answering over incomplete KGs (KGQA).
Ranked #6 on
Link Prediction
on Wikidata5M
Question Answering Over Temporal Knowledge Graphs
Temporal Knowledge Graphs (Temporal KGs) extend regular Knowledge Graphs by providing temporal scopes (start and end times) on each edge in the KG.
Ranked #4 on
Question Answering
on Complex-CronQuestions
Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings
In a separate line of research, KG embedding methods have been proposed to reduce KG sparsity by performing missing link prediction.
Ranked #6 on
Question Answering
on MultiTQ
