13 papers
Evaluating Pluralism in LLMs through Latent Perspectives
Laura Majer, Jan Å najder, Martin Tutek
The growing need to represent diverse perspectives has increased interest in pluralistic LLM generation. Although difficult to operationalize, identifying perspectives expressed in…
Reasoning Models Know What's Important, and Encode It in Their Activations
Yaniv Nikankin, Martin Tutek, Tomer Ashuach +2
Language models often solve complex tasks by generating long reasoning chains, consisting of many steps with varying importance. While some steps are crucial for generating the fin…
Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
Adi Simhi, Fazl Barez, Martin Tutek +2
How does the conversational past of large language models (LLMs) influence their future performance? Recent work suggests that LLMs are affected by their conversational history in…
CRISP: Persistent Concept Unlearning via Sparse Autoencoders
Tomer Ashuach, Dana Arad, Aaron Mueller +2
As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preserving model utility has become pa…
ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
Adi Simhi, Jonathan Herzig, Martin Tutek +3
As large language models (LLMs) evolve from conversational assistants into autonomous agents, evaluating the safety of their actions becomes critical. Prior safety benchmarks have…
Context Parametrization with Compositional Adapters
Josip JukiÄ, Martin Tutek, Jan Å najder
Large language models (LLMs) often seamlessly adapt to new tasks through in-context learning (ICL) or supervised fine-tuning (SFT). However, ICL is inefficient when handling many d…