collaborators

8 papers

cs.CL2026

Reasoning Fine-Tuning Induces Persistent Latent Policy States

Abir Harrasse, Michael Lan, Hunar Batra +2

Reasoning-specialized language models show large performance gains over base models, yet the internal changes responsible for improved multi-step reasoning remain poorly understood…

cs.LG2026

STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations

Rishit Dagli, Abir Harrasse, Luke Zhang +4

Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data. The gold standard for TDA relies on causal interventions, observing how a model chan…

cs.LG2026

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs

Florent Draye, Abir Harrasse, Vedant Palit +8

Mechanistic interpretability seeks to understand how Large Language Models (LLMs) represent and process information. Recent approaches based on dictionary learning and transcoders…

cs.AI2026

Curveball Steering: The Right Direction To Steer Isn't Always Linear

Shivam Raval, Hae Jin Song, Linlin Wu +4

Activation steering is a widely used approach for controlling large language model (LLM) behavior by intervening on internal representations. Existing methods largely rely on the L…

cs.CL2026

Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders

Abir Harrasse, Florent Draye, Punya Syon Pandey +2

Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they form shared multilingual representat…

cs.CL2026

Debate, Deliberate, Decide (D3): A Cost-Aware Adversarial Framework for Reliable and Interpretable LLM Evaluation

Abir Harrasse, Chaithanya Bandi, Hari Bandi

The evaluation of Large Language Models (LLMs) remains challenging due to inconsistency, bias, and the absence of transparent decision criteria in automated judging. We present Deb…