4 papers
Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG
Agam Goyal, Koyel Mukherjee, Apoorv Saxena +3
Dense retrievers in retrieval-augmented generation (RAG) systems exhibit systematic biases -- including brevity, position, literal matching, and repetition biases -- that can compr…
ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
Nikhil Anand, Shwetha Somasundaram, Anirudh Phukan +2
Large Language Models (LLMs) encode vast amounts of parametric knowledge during pre-training. As world knowledge evolves, effective deployment increasingly depends on their ability…
Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs
Anirudh Phukan, Divyansh, Harshit Kumar Morj +3
The rapid development of Large Multimodal Models (LMMs) has significantly advanced multimodal understanding by harnessing the language abilities of Large Language Models (LLMs) and…
PLD+: Accelerating LLM inference by leveraging Language Model Artifacts
Shwetha Somasundaram, Anirudh Phukan, Apoorv Saxena
To reduce the latency associated with autoretrogressive LLM inference, speculative decoding has emerged as a novel decoding paradigm, where future tokens are drafted and verified i…