6 citations · 17 across the 32 of their papers we have counts for
13 papers · 1 filter
MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi +7
As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal…
A Survey on LLM-based Conversational User Simulation
Bo Ni, Leyao Wang, Yu Wang +27
User simulation has long played a vital role in computer science due to its potential to support a wide range of applications. Language, as the primary medium of human communicatio…
Reasoning-Based Personalized Generation for Users with Sparse Data
Bo Ni, Branislav Kveton, Samyadeep Basu +14
Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history. However, real-world users usually possess sparse…
Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models
Sriram Balasubramanian, Samyadeep Basu, Koustava Goswami +6
Large language models (LLMs) are increasingly used for long-document question answering, where reliable attribution to sources is critical for trust. Existing post-hoc attribution…
Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis
Anushka Yadav, Isha Nalawade, Srujana Pillarichety +7
The emergence of reasoning models and their integration into practical AI chat bots has led to breakthroughs in solving advanced math, deep search, and extractive question answerin…
A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations
Li Li, Peilin Cai, Ryan A. Rossi +21
We present PersonaConvBench, a large-scale benchmark for evaluating personalized reasoning and generation in multi-turn conversations with large language models (LLMs). Unlike exis…
A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models
Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi
Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes…
On Mechanistic Circuits for Extractive Question-Answering
Samyadeep Basu, Vlad Morariu, Zichao Wang +4
Large language models are increasingly used to process documents and facilitate question-answering on them. In our paper, we extract mechanistic circuits for this real-world langua…
A Survey of Small Language Models
Chien Van Nguyen, Xuan Shen, Ryan Aponte +25
Small Language Models (SLMs) have become increasingly important due to their efficiency and performance to perform various language tasks with minimal computational resources, maki…
Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis
Reshmi Ghosh, Rahul Seetharaman, Hitesh Wadhwa +6
Retrieval Augmented Generation (RAG) is a widely used approach for leveraging external context in several natural language applications such as question answering and information r…
From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries
Hitesh Wadhwa, Rahul Seetharaman, Somyaa Aggarwal +6
Retrieval Augmented Generation (RAG) enriches the ability of language models to reason using external context to augment responses for a given user prompt. This approach has risen…
Topic Segmentation of Semi-Structured and Unstructured Conversational Datasets using Language Models
Reshmi Ghosh, Harjeet Singh Kajal, Sharanya Kamath +4
Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many d…
On Surgical Fine-tuning for Language Encoders
Abhilasha Lodha, Gayatri Belapurkar, Saloni Chalkapurkar +5
Fine-tuning all the layers of a pre-trained neural language encoder (either using all the parameters or using parameter-efficient methods) is often the de-facto way of adapting it…