works on

From the 1 of 18 linked papers with an AI index.

activity
20242026
collaborators

18 papers

cs.AI2026

Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures

Harsh Raj, Vipul Gupta, Anas Mahmoud +4

Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the agent system. This creates…

cs.AI2026

CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data

Vipul Gupta, Zihao Wang, Razvan-Gabriel Dumitru +3

Evaluations should do more than measure a models current performance. They should tell us what to fix for the next model iteration and provide a way to generate targeted post train…

cs.DL2026

The INRIA DataLake: A Generic and Scalable Ecosystem of Pipelines for HAL Applied to Software Mentions Tracking

Luca Foppiano, Vipul Gupta, Samuel Scalbert +6

The paper describes the INRIA DataLake, a scalable ecosystem of interconnected pipelines that prepares scientific articles, extracts structured information such as software mention…

cs.CL2026

Model Unlearning Objectives Vary for Distinct Language Functions

Berk Atil, Vipul Gupta, Rebecca J. Passonneau

Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-training uses different objectiv…

cs.IR2026

HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval

Vipul Gupta, Shikhar Mohan, Lakshya Kumar +4

In the competitive landscape of sponsored search, balancing retrieval quality with production latency is a critical challenge. While large retrieval models based on Small Language…

cs.CL2026

BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks

Nishant Balepur, Bhavya Rajasekaran, Jane Oh +7

Multiple-choice question answering (MCQA) is standard in NLP, but benchmarks lack rigorous quality control. We present BenchMarker, an education-inspired toolkit using LLM judges t…