21 citations · 34 across the 35 of their papers we have counts for
18 papers · 1 filter
AuditKIT: A Unified Evaluation Spine for Benchmarking, Judging, and Comparing Large Language Models and Agentic Systems
Shreeyans Arora, Utsav Avaiya, Zera Lyngkhoi +4
Evaluating language models and agents requires combining benchmark accuracy, judge-based assessment, runtime performance, tool-use behavior, and retrieval quality. Differences in i…
Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair
Areeb Ahmad, Pratinav Seth, Vinay Kumar Sankarapu
Ablate a component of a language model, and other components often appear to adjust and compensate. This phenomenon, termed self-repair, has been observed repeatedly, but its mecha…
SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs
Pratinav Seth, Saisab Sadhu, Anshul Kaushal +1
Methods for addressing safety drift in fine-tuned Large Language Models (LLMs) are scattered across incompatible implementations, lifecycle stages, and evaluation protocols, making…
What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models
Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu +1
Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data pr…
CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
Pratinav Seth, Hem Gosalia, Aditya Kasliwal +1
Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning. However, conducting such an…
Faithfulness to Refusal: A Causal Audit of Neuron Selectors
Ananth Eswar, Pratinav Seth, Utsav Avaiya +1
Attribution scores increasingly identify which neuron rows of a language model matter for applications such as pruning, interpretability, and editing for safety, yet whether they i…
CuratorKIT : Data Curation and Synthetic Data Generation for LLM Post-Training
Soham Bhattacharjee, Karun Sharma, Vinay Kumar Sankarapu +1
Data curation is a critical part of post-training pipelines for large language models, yet existing tools often treat ingestion, deduplication, synthetic generation, and quality fi…
ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing
Chirag Chawla, Pratinav Seth, Vinay Kumar Sankarapu
Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language. Existing inference-time defen…
Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation
Soham Bhattacharjee, Karun Sharma, Vinay Kumar Sankarapu +1
Synthetic post-training pipelines commonly filter generated samples with reward models or holistic LLM judges, yet two practices remain rarely examined together: whether the filter…
Distilling Tabular Foundation Models for Structured Health Data
Aditya Tanna, Nassim Bouarour, Mohamed Bouadi +2
Tabular foundation models (TFMs) achieve strong performance on health datasets, but their inference cost and infrastructure requirements limit practical use. We study whether their…
Ensembling Tabular Foundation Models - A Diversity Ceiling And A Calibration Trap
Aditya Tanna, Yash Desai, Pratinav Seth +3
Tabular foundation models (TFMs) now match or beat tuned gradient-boosted trees on a growing fraction of tabular tasks, but no single TFM wins on every dataset. Ensembling is the g…
Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees
Aditya Tanna, Nassim Bouarour, Mohamed Bouadi +2
A fraud scorer needs to answer in under 2 ms. The best tabular foundation models (TFMs) take 151-1,275 ms on GPU. We close this gap by distilling the TFM offline into an XGBoost or…
Data Presentation Over Architecture: Resampling Strategies for Credit Risk Prediction with Tabular Foundation Models
Aditya Tanna, Mitul Solanki, Mohamed Bouadi +3
Credit default prediction is a tabular learning problem with severe class imbalance, heterogeneous features, and tight latency budgets. Tabular Foundation Models (TFMs) approach th…
Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands
Pratinav Seth, Vinay Kumar Sankarapu
This position paper argues that behavioural assurance, even when carefully designed, is being asked to carry safety claims it cannot verify. AI governance frameworks enacted betwee…
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
Saisab Sadhu, Pratinav Seth, Vinay Kumar Sankarapu
Standard unlearning evaluations measure behavioral suppression in full precision, immediately after training, despite every deployed language model being quantized first. Recent wo…
AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
R E Zera Marveen Lyngkhoi, Chirag Chawla, Pratinav Seth +5
Post-training alignment is central to deploying large language models (LLMs), yet practical workflows remain split across backend-specific tools and ad-hoc glue code, making experi…
-: Circuit-Restricted Weight Arithmetic for Selective Refusal
Aditya Kasliwal, Pratinav Seth, Vinay Kumar Sankarapu
Modern deployments require LLMs to enforce safety policies at scale, yet many controls rely on inference-time interventions that add recurring compute cost and serving complexity.…
Exploring Fine-Tuning for Tabular Foundation Models
Aditya Tanna, Pratinav Seth, Mohamed Bouadi +1
Tabular Foundation Models (TFMs) have recently shown strong in-context learning capabilities on structured data, achieving zero-shot performance comparable to traditional machine l…