相关论文: Trust but Verify: Prover-Verifier Deliberation for…

Autoregressive (AR) decoding is a major latency bottleneck for large language models. Speculative decoding (SD) accelerates AR by letting a drafter propose multi-token blocks that a verifier accepts or rejects. However, many SD systems…

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…

Nowadays, the quality of responses generated by different modern large language models (LLMs) is hard to evaluate and compare automatically. Recent studies suggest and predominantly use LLMs for reference-free evaluation of open-ended…

Retrieval-augmented language models can retrieve relevant evidence yet still commit to answers before explicitly checking whether the retrieved context supports the conclusion. We present PAVE (Premise-Grounded Answer Validation and…

Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We introduce CoRefine, a confidence-guided self-refinement…

Language models (LMs) are statistical models trained to assign probability to human-generated text. As such, it is reasonable to question whether they approximate linguistic variability exhibited by humans well. This form of statistical…

AI Safety is a major concern in many deep learning applications such as autonomous driving. Given a trained deep learning model, an important natural problem is how to reliably verify the model's prediction. In this paper, we propose a…

Conformal prediction provides rigorous distribution-free finite-sample guarantees for marginal coverage under the assumption of exchangeability, but may exhibit systematic undercoverage or overcoverage for specific subpopulations. Assessing…

Vision-language process reward models (VL-PRMs) are increasingly used to score intermediate reasoning steps and rerank candidates under test-time scaling. However, they often function as black-box judges: a low step score may reflect a…

Validation accuracy is a necessary, but not sufficient, measure of a neural network classifier's quality. High validation accuracy during development does not guarantee that a model is free of serious flaws, such as vulnerability to…

Recent work identifies a stated-revealed (SvR) preference gap in language models (LMs): a mismatch between the values models endorse and the choices they make in context. Existing evaluations rely heavily on binary forced-choice prompting,…

In this paper, we propose a novel way of addressing text-dependent automatic speaker verification (TD-ASV) by using a shared-encoder with task-specific decoders. An autoregressive predictive coding (APC) encoder is pre-trained in an…

As AI systems migrate to safety-critical domains, verifying that their actions comply with well-defined rules remains a challenge. Formal methods provide provable guarantees but demand hand-crafted temporal-logic specifications, offering…

Value model guided search is effective in steering LLM generation but suffers from a lack of robustness. This is due to verifier failure: imperfect VMs mistakenly prune valid reasoning paths, especially when encountering unseen reasoning…

Cross-validation (CV) is a popular approach for assessing and selecting predictive models. However, when the number of folds is large, CV suffers from a need to repeatedly refit a learning procedure on a large number of training datasets.…

Prompt-based verification is widely used to mitigate hallucinations in large vision-language models (LVLMs), yet when it helps remains poorly understood. We systematically study verification prompting across two representative LVLM…

Do large language models (LLMs) anticipate when they will answer correctly? To study this, we extract activations after a question is read but before any tokens are generated, and train linear probes to predict whether the model's…

In black-box large language model (LLM) services, response reliability is often only partially observable at decision time, while stronger inference pathways incur substantial computational cost, inducing a budgeted sequential decision…

Reinforcement learning with verifiable rewards (RLVR) is a simple but powerful paradigm for training LLMs: sample a completion, verify it, and update. In practice, however, the verifier is almost never clean--unit tests probe only limited…