Related papers: Demonstrating specification gaming in reasoning mo…

We investigate the robustness of reasoning models trained for step-by-step problem solving by introducing query-agnostic adversarial triggers - short, irrelevant text that, when appended to math problems, systematically mislead models to…

Implicit biases refer to automatic mental processes that shape perceptions, judgments, and behaviors. Previous research on "implicit bias" in LLMs focused primarily on outputs rather than the processes underlying the outputs. We present the…

Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems. In cyber-security, there have been multiple research…

The rapid rise of large language models (LLMs) has shifted artificial intelligence (AI) research toward agentic systems, motivating the use of weaker and more flexible notions of agency. However, this shift raises key questions about the…

The field of software security testing, more specifically penetration testing, is an activity that requires high levels of expertise and involves many manual testing and analysis steps. This paper explores the potential usage of…

The research builds and evaluates the adversarial potential to introduce copied code or hallucinated AI recommendations for malicious code in popular code repositories. While foundational large language models (LLMs) from OpenAI, Google,…

DeepSeek recently released R1, a high-performing large language model (LLM) optimized for reasoning tasks. Despite its efficient training pipeline, R1 achieves competitive performance, even surpassing leading reasoning models like OpenAI's…

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…

Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By allocating more computational resources during the inference…

Contemporary large language models are powerful problem-solving tools, but they exhibit weaknesses in their reasoning abilities which ongoing research seeks to mitigate. We investigate graph coloring as a means of evaluating an LLM's…

As large language models (LLMs) grow more capable, concerns about their safe deployment have also grown. Although alignment mechanisms have been introduced to deter misuse, they remain vulnerable to carefully designed adversarial prompts.…

Large Language Models (LLMs) have emerged as powerful tools for software development tasks such as code completion, translation, and optimization. However, their ability to generate efficient and correct code, particularly in complex…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Test-time scaling has enabled Large Language Models (LLMs) with remarkable reasoning capabilities, particularly in mathematical domains, through intermediate chain-of-thought (CoT) reasoning before generating final answers. However, the…

Large Language Models (LLMs) have demonstrated remarkable emergent capabilities, yet the robustness of their numerical reasoning remains an open question. While standard benchmarks evaluate LLM reasoning on complex problem sets using…

Large Language Models (LLMs) trained via Reinforcement Learning (RL) have recently achieved impressive results on reasoning benchmarks. Yet, growing evidence shows that these models often generate longer but ineffective chains of thought…

Large Language Models (LLMs) have been touted as AI models possessing advanced reasoning abilities. However, recent works have shown that LLMs often bypass true reasoning using shortcuts, sparking skepticism. To study the reasoning…

Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even…

Behavioral simulation and strategic problem solving are different tasks. Large language models are increasingly explored as agents in policy-facing institutional simulations, but stronger reasoning need not improve behavioral sampling. We…