1 citations · 1 across the 11 of their papers we have counts for
12 papers
Many Biases, One Circuit: Post-Training Tunes a Pretrained Cue-Routing Mechanism
Prakhar Gupta, Terry Jingchen Zhang, Zhijing Jin
Language models often abandon a correct answer when the prompt contains a cue, a hint toward a wrong option such as "I think the answer is B." Sycophancy and related biases show th…
RAPTOR: Role-Aware Private Training for Mixture-of-Experts
Duc Dm, Khai Le-Duc, Nguyen Do +18
Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see all data while experts only se…
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?
Prakhar Gupta, Terry Jingchen Zhang, Florent Draye +2
Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant…
How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution
Vedant Palit, Florent Draye, Terry Jingchen Zhang +2
Transcoder attribution graphs are usually trained to explain why a model assigns high probability to a particular next token. We introduce Concept-Targeted Attribution (CTA), which…
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR
Yongjin Yang, Jiarui Liu, Yinghui He +3
Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science.…
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…
PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding
Duc Cao Dinh, Khai Le-Duc, Florent Draye +4
3D Visual Grounding (3DVG) aims to localize target objects in 3D scenes given natural language descriptions. Existing approaches typically perform reasoning over the entire scene,…
Evaluating Second-Order Bias of LLMs Through Epistemic Entitlement
Ramaravind Kommiya Mothilal, Terry Jingchen Zhang, Raiyan Ahmed +3
Evaluations of social bias in LLMs largely focus on whether models generate or imply biased content. However, as LLMs are increasingly used as judges of bias, they may exhibit soci…
Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution
Ruta Binkyte, Ivaxi Sheth, Zhijing Jin +3
As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), are increasingly deployed in high-stakes domains, ensuring their trustworthines…
CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs
Florent Draye, Vedant Palit, Abir Harrasse +8
Mechanistic interpretability seeks to understand how Large Language Models (LLMs) represent and process information. Recent approaches based on dictionary learning and transcoders…
BinaryPPO: Efficient Policy Optimization for Binary Classification
Punya Syon Pandey, Zhijing Jin
Supervised fine-tuning (SFT) is the standard approach for binary classification tasks such as toxicity detection, factuality verification, and causal inference. However, SFT often…
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey +8
As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, be…