相关论文: Verde: Verification via Refereed Delegation for Ma…

Software vulnerability detection (SVD) is a critical challenge in modern systems. Large language models (LLMs) offer natural-language explanations alongside predictions, but most work focuses on binary evaluation, and explanations often…

Large Language Models (LLMs) show great promise in complex reasoning, with Reinforcement Learning with Verifiable Rewards (RLVR) being a key enhancement strategy. However, a prevalent issue is ``superficial self-reflection'', where models…

The increasing use of Retrieval-Augmented Generation (RAG) systems in various applications necessitates stringent protocols to ensure RAG systems accuracy, safety, and alignment with user intentions. In this paper, we introduce VERA…

As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previous work introduced control evaluations, an adversarial…

The proliferation of large language models (LLMs) has led to the adoption of Mixture-of-Experts (MoE) architectures that dynamically leverage specialized subnetworks for improved efficiency and performance. Despite their benefits, MoE…

In contemporary workplaces, meetings are essential for exchanging ideas and ensuring team alignment but often face challenges such as time consumption, scheduling conflicts, and inefficient participation. Recent advancements in Large…

The requirements engineering (RE) phase is pivotal in developing high-quality software. Integrating advanced modelling techniques with large language models (LLMs) and formal verification in a logical style can significantly enhance this…

With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method GRPO faces failure due to insignificant reward variance, while verification methods based on process reward models (PRMs) suffer…

Grid computing infrastructures need to provide traceability and accounting of their users" activity and protection against misuse and privilege escalation. A central aspect of multi-user Grid job environments is the necessary delegation of…

Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference-time protocol grounded in interactive proof theory, as a mechanism for selective…

We present new algorithms for a posteriori verification of neural networks (NNs) approximating solutions to PDEs. These verification algorithms compute accurate estimates of $L^p$ norms of NNs and their derivatives. When combined with…

We initiate an investigation of learning tasks in a setting where the learner is given access to two competing provers, only one of which is honest. Specifically, we consider the power of such learners in assessing purported properties of…

Large Language Models (LLMs) excel in natural language processing tasks but pose significant computational and memory challenges for edge deployment due to their intensive resource demands. This work addresses the efficiency of LLM…

As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environments (TEEs), which…

Recent advances in large reasoning models have leveraged reinforcement learning with verifiable rewards (RLVR) to improve reasoning capabilities. However, scaling these methods typically requires extensive rollout computation and large…

The rapid integration of Large Language Models (LLMs) into decentralized physical infrastructure networks (DePIN) is currently bottlenecked by the Verifiability Trilemma, which posits that a decentralized inference system cannot…

Vision-Language Models (VLMs) often generate plausible but incorrect responses to visual queries. However, reliably quantifying the effect of such hallucinations in free-form responses to open-ended queries is challenging as it requires…

Uncertainty quantification for partial differential equations is traditionally grounded in discretization theory, where solution error is controlled via mesh/grid refinement. Physics-informed neural networks fundamentally depart from this…

We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruction-following, helpfulness, safety) by maximizing the…

Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem. While numerous approaches have been proposed…