6 citations · 24 across the 44 of their papers we have counts for
27 papers · 1 filter
A Sense of Proprioception in Language Models
Jonas Geiping
In humans, proprioception corresponds to the sense of self-movement or position, e.g. understanding the position of one's arm. This sense is often less well-understood and in popul…
Attractor States Emerge in Multi-Turn LLM Conversations
Ting-Wen Ko, Jonas Geiping
Large language models (LLMs) are increasingly used in open-ended multi-agent settings, but the long-run dynamics of model--model interaction remain poorly understood. We study whet…
FutureSim: Replaying World Events to Evaluate Adaptive Agents
Shashwat Goel, Nikhil Chandak, Arvindh Arun +5
AI agents are being increasingly deployed in dynamic, open-ended environments that require adapting to new information as it arrives. To efficiently measure this capability for rea…
Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
Guinan Su, Yanwu Yang, Xueyan Li +1
The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or computer use applications. Howe…
Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees
Xueyan Li, Johannes Zenn, Ekaterina Fadeeva +3
Self-consistency boosts inference-time performance by sampling multiple reasoning traces in parallel and voting. However, in constrained domains like math and code, this strategy i…
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
Alexander Panfilov, Peter Romov, Igor Shilov +3
We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injecti…
Scaling Open-Ended Reasoning to Predict the Future
Nikhil Chandak, Shashwat Goel, Ameya Prabhu +2
High-stakes decision making involves reasoning under uncertainty about the future. In this work, we train language models to make predictions on open-ended forecasting questions. T…
Training AI Co-Scientists Using Rubric Rewards
Shashwat Goel, Rishi Hazra, Dulhan Jayalath +8
AI co-scientists are emerging as a tool to assist human researchers in achieving their research goals. A crucial feature of these AI co-scientists is the ability to generate a rese…
Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models
Jonas Geiping, Xinyu Yang, Guinan Su
Language models with recurrent depth, also referred to as universal or looped when considering transformers, are defined by the capacity to increase their computation through the r…
Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs
Xueyan Li, Guinan Su, Mrinmaya Sachan +1
Large Language Models (LLMs) are increasingly applied to complex tasks that require extended reasoning. In such settings, models often benefit from diverse chains-of-thought to arr…
When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs
Keyu Wang, Tian Lyu, Guinan Su +4
Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs). Although existing methods demonstrate strong performance reten…
Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou +4
AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testin…
Training Dynamics Impact Post-Training Quantization Robustness
Albert Catalan-Tatjer, Niccolò Ajroldi, Jonas Geiping
While post-training quantization is widely adopted for efficient deployment of large language models, the mechanisms underlying quantization robustness remain unclear. We conduct a…
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
Alexander Panfilov, Evgenii Kortukov, Kristina Nikolić +6
Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrifici…
Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling
Teodora Srećković, Jonas Geiping, Antonio Orvieto
Adam is known to perform significantly better than Stochastic Gradient Descent (SGD) in language models, a phenomenon for which a number of explanations have been proposed. In this…
Pitfalls in Evaluating Language Model Forecasters
Daniel Paleka, Shashwat Goel, Jonas Geiping +1
Large language models (LLMs) have recently been applied to forecasting tasks, with some works claiming these systems match or exceed human performance. In this paper, we argue that…
Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language Models
Fay Elhassan, Niccolò Ajroldi, Antonio Orvieto +1
The indistinguishability of AI-generated content from human text raises challenges in transparency and accountability. While several methods exist to watermark models behind APIs,…
Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation
Shiven Sinha, Shashwat Goel, Ponnurangam Kumaraguru +3
There is growing excitement about the potential of Language Models (LMs) to accelerate scientific discovery. Falsifying hypotheses is key to scientific progress, as it allows claim…
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Jonas Geiping, Sean McLeish, Neel Jain +6
We study a novel language model architecture that is capable of scaling test-time computation by implicitly reasoning in latent space. Our model works by iterating a recurrent bloc…
Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers
Siddharth Singh, Prajwal Singhania, Aditya Ranjan +9
Training and fine-tuning large language models (LLMs) with hundreds of billions to trillions of parameters requires tens of thousands of GPUs, and a highly scalable software stack.…
When, Where and Why to Average Weights?
Niccolò Ajroldi, Antonio Orvieto, Jonas Geiping
Averaging checkpoints along the training trajectory is a simple yet powerful approach to improve the generalization performance of Machine Learning models and reduce training time.…
Great Models Think Alike and this Undermines AI Oversight
Shashwat Goel, Joschka Struber, Ilze Amanda Auzina +6
As Language Model (LM) capabilities advance, evaluating and supervising them at scale is getting harder for humans. There is hope that other language models can automate both these…
An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks
Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek +2
A plethora of jailbreaking attacks have been proposed to obtain harmful responses from safety-tuned LLMs. These methods largely succeed in coercing the target output in their origi…
LMD3: Language Model Data Density Dependence
John Kirchenbauer, Garrett Honke, Gowthami Somepalli +5
We develop a methodology for analyzing language model task performance at the individual example level based on training data density estimation. Experiments with paraphrasing as a…