11 papers
@GrokSet: multi-party Human-LLM Interactions in Social Media
Matteo Migliarini, Berat Ercevik, Oluwagbemike Olowe +5
Large Language Models (LLMs) are increasingly deployed as active participants on public social media platforms, yet their behavior in these unconstrained social environments remain…
A Few Bad Neurons: Isolating and Surgically Correcting Sycophancy
Claire O'Brien, Jessica Seto, Dristi Roy +6
Behavioral alignment in large language models (LLMs) is often achieved through broad fine-tuning, which can result in undesired side effects like distributional shift and low inter…
Peek-a-Boo Reasoning: Contrastive Region Masking in MLLMs
Isha Chaturvedi, Anjana Nair, Yushen Li +5
We introduce Contrastive Region Masking (CRM), a training free diagnostic that reveals how multimodal large language models (MLLMs) depend on specific visual regions at each step o…
SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
Shourya Batra, Pierce Tillman, Samarth Gaggar +6
As Large Language Models (LLMs) evolve into personal assistants with access to sensitive user data, they face a critical privacy challenge: while prior work has addressed output-le…
Modeling and Predicting Multi-Turn Answer Instability in Large Language Models
Jiahang He, Rishi Ramachandran, Neel Ramachandran +5
As large language models (LLMs) are adopted in an increasingly wide range of applications, user-model interactions have grown in both frequency and scale. Consequently, research ha…
Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits
Dev Patel, Gabrielle Gervacio, Diekola Raimi +5
Large Language Models require substantial computational resources for inference, posing deployment challenges. While dynamic pruning offers superior efficiency over static methods…
Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
Daniel Aarao Reis Arturi, Eric Zhang, Andrew Ansah +3
Recent work has discovered that large language models can develop broadly misaligned behaviors after being fine-tuned on narrowly harmful datasets, a phenomenon known as emergent m…
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
Nikita Afonin, Nikita Andriianov, Vahagn Hovhannisyan +9
Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning, these findings were limited to f…
LIFT: Likelihood-Based Intervention Faithfulness Training
Anand Swaroop, Akshat Nallani, Saksham Uboweja +7
Chain-of-thought (CoT) reasoning improves LLM accuracy on complex tasks, but CoTs are often unfaithful; that is, the model does not rely on the stated reasoning steps to produce it…
Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization
Nathan Egbuna, Saatvik Gaur, Sunishchal Dev +2
Test-time optimization remains impractical at scale due to prohibitive inference costs--techniques like iterative refinement and multi-step verification can require …
Evaluation Awareness Scales Predictably in Open-Weights Large Language Models
Maheep Chaudhary, Ian Su, Nikhil Hooda +6
Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety eval…