565 citations · 711 across the 35 of their papers we have counts for
7 papers · 1 filter
Adversarial Lens: Exploiting Attention Layers to Generate Adversarial Examples for Evaluation
Kaustubh Dhole
Recent advances in mechanistic interpretability suggest that intermediate attention layers encode token-level hypotheses that are iteratively refined toward the final output. In th…
Toward Honest Language Models for Deductive Reasoning
Jiarui Liu, Kaustubh Dhole, Yingheng Wang +7
Deductive reasoning is the process of deriving conclusions strictly from the given premises, without relying on external knowledge. We define honesty in this setting as a model's a…
Evaluating Hybrid Retrieval Augmented Generation using Dynamic Test Sets: LiveRAG Challenge
Chase Fensore, Kaustubh Dhole, Joyce C Ho +1
We present our submission to the LiveRAG Challenge 2025, which evaluates retrieval-augmented generation (RAG) systems on dynamic test sets using the FineWeb-10BT corpus. Our final…
InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking
Rahul Seetharaman, Kaustubh D. Dhole, Aman Bansal
Large Language Models (LLMs) have demonstrated significant strides across various information retrieval tasks, particularly as rerankers, owing to their strong generalization and k…
Generative Product Recommendations for Implicit Superlative Queries
Kaustubh D. Dhole, Nikhita Vedula, Saar Kuzi +3
In Recommender Systems, users often seek the best products through indirect, vague, or under-specified queries, such as "best shoes for trail running". Such queries, also referred…
A Multi-Encoder Frozen-Decoder Approach for Fine-Tuning Large Language Models
Kaustubh D. Dhole
Among parameter-efficient fine-tuning methods, freezing has emerged as a popular strategy for speeding up training, reducing catastrophic forgetting, and improving downstream perfo…
To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation
Kaustubh D. Dhole
Retrieval-Augmented Generation equips large language models with the capability to retrieve external knowledge, thereby mitigating hallucinations by incorporating information beyon…