相关论文: Likelihood hacking in probabilistic program synthe…

A trustworthy real-world prediction system should produce well-calibrated confidence scores; that is, its confidence in an answer should be indicative of the likelihood that the answer is correct, enabling deferral to an expert in cases of…

While recent code-specific large language models (LLMs) have greatly enhanced their code generation capabilities, the safety of these models remains under-explored, posing potential risks as insecure code generated by these models may…

Probabilistic Programming Languages (PPLs) are a powerful tool in machine learning, allowing highly expressive generative models to be expressed succinctly. They couple complex inference algorithms, implemented by the language, with an…

Real-world reinforcement learning (RL) problems often demand that agents behave safely by obeying a set of designed constraints. We address the challenge of safe RL by coupling a safety guide based on model predictive control (MPC) with a…

Despite widespread success in language understanding and generation, large language models (LLMs) exhibit unclear and often inconsistent behavior when faced with tasks that require probabilistic reasoning. In this work, we present the first…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Reinforcement Learning from Verifiable Rewards (RLVR) has recently shown that large language models (LLMs) can develop their own reasoning without direct supervision. However, applications in the medical domain, specifically for question…

We investigate the radioactivity of text generated by large language models (LLM), i.e. whether it is possible to detect that such synthetic input was used to train a subsequent LLM. Current methods like membership inference or active IP…

LLM-based programming assistants offer the promise of programming faster but with the risk of introducing more security vulnerabilities. Prior work has studied how LLMs could be maliciously fine-tuned to suggest vulnerabilities more often.…

Prediction sets provide a theoretically grounded framework for quantifying uncertainty in machine learning models. Adapting them to structured generation tasks, in particular, large language model (LLM) based code generation, remains a…

We present a probabilistic logic programming framework to reinforcement learning, by integrating reinforce-ment learning, in POMDP environments, with normal hybrid probabilistic logic programs with probabilistic answer set seman-tics, that…

As large language models (LLMs) transition from chat interfaces to integral components of stochastic pipelines and systems approaching general intelligence, the ability to faithfully sample from specified probability distributions has…

We study the theoretical consequence of p-hacking on the accumulation of knowledge under the framework of mis-specified Bayesian learning. A sequence of researchers, in turn, choose projects that generate noisy information in a field. In…

Large Language Models (LLMs) are redefining offensive cybersecurity by allowing the generation of harmful machine code with minimal human intervention. While attackers take advantage of dark LLMs such as XXXGPT and WolfGPT to produce…

LLMs are widely used for code generation and mathematical reasoning tasks where they are required to generate structured output. They either need to reason about code, generate code for a given specification, or reason using programs of…

Designing reliable decision strategies for autonomous urban driving is challenging. Reinforcement learning (RL) has been used to automatically derive suitable behavior in uncertain environments, but it does not provide any guarantee on the…

One of the long-standing goals in optimisation and constraint programming is to describe a problem in natural language and automatically obtain an executable, efficient model. Large language models appear to bring this vision closer,…

Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundamental trade-off:…

Reinforcement Learning (RL) suffers from sample inefficiency in sparse reward domains, and the problem is further pronounced in case of stochastic transitions. To improve the sample efficiency, reward shaping is a well-studied approach to…

Large Language Models (LLMs) are increasingly applied to automate software engineering tasks, including the generation of UML class diagrams from natural language descriptions. While prior work demonstrates that LLMs can produce…