Related papers: Mitigating LLM Hallucination via Behaviorally Cali…
Large language models (LLMs) are known to "hallucinate" by generating false or misleading outputs. Hallucinations pose various harms, from erosion of trust to widespread misinformation. Existing hallucination evaluation, however, focuses…
Large foundation models (LFMs) are susceptible to two distinct vulnerabilities: hallucinations and jailbreak attacks. While typically studied in isolation, we observe that defenses targeting one often affect the other, hinting at a deeper…
Hallucinations in large language models (LLMs), plausible but factually inaccurate text, are often viewed as undesirable. However, recent work suggests that such outputs may hold creative potential. In this paper, we investigate whether…
We prove a fundamental impossibility theorem: neural networks cannot simultaneously learn well-calibrated confidence estimates with meaningful diversity when trained using binary correct/incorrect supervision. Through rigorous mathematical…
Hallucination in Large Language Models (LLMs) is a well studied problem. However, the properties that make LLM intrinsically vulnerable to hallucinations have not been identified and studied. This research identifies and characterizes the…
Large Language Models (LLMs) frequently generate plausible but non-factual content, a phenomenon known as hallucination. While existing detection methods typically rely on computationally expensive sampling-based consistency checks or…
Continual Learning (CL) focuses on maximizing the predictive performance of a model across a non-stationary stream of data. Unfortunately, CL models tend to forget previous knowledge, thus often underperforming when compared with an offline…
This paper investigates how hallucination rates in Large Language Models (LLMs) may be controlled via a symbolic data generation framework, exploring a fundamental relationship between the rate of certain mathematical errors and types of…
Mathematical reasoning models are widely deployed in education, automated tutoring, and decision support systems despite exhibiting fundamental computational instabilities. We demonstrate that state-of-the-art models (Qwen2.5-Math-7B)…
Calibration is commonly evaluated by comparing model confidence with its empirical correctness, implicitly treating reliability as a function of the confidence score alone. However, this view can hide substantial structure: models may be…
Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignment process fails to…
Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a…
Despite the outstanding performance of large language models (LLMs) across various NLP tasks, hallucinations in LLMs--where LLMs generate inaccurate responses--remains as a critical problem as it can be directly connected to a crisis of…
Reinforcement finetuning (RFT) has become a standard approach for enhancing the reasoning capabilities of large language models (LLMs). However, its impact on model trustworthiness remains underexplored. In this work, we identify and…
We show that language models hallucinate not because they fail to detect uncertainty, but because of a failure to integrate it into output generation. Across architectures, uncertain inputs are reliably identified, occupying…
This study addresses the critical challenge of hallucination mitigation in Large Vision-Language Models (LVLMs) for Visual Question Answering (VQA) tasks through a Split Conformal Prediction (SCP) framework. While LVLMs excel in multi-modal…
Multilingual pre-trained Large Language Models (LLMs) are incredibly effective at Question Answering (QA), a core task in Natural Language Understanding, achieving high accuracies on several multilingual benchmarks. However, little is known…
Hallucinations pose a significant challenge to the reliability and alignment of Large Language Models (LLMs), limiting their widespread acceptance beyond chatbot applications. Despite ongoing efforts, hallucinations remain a prevalent…
Instruction-following Vision Large Language Models (VLLMs) have achieved significant progress recently on a variety of tasks. These approaches merge strong pre-trained vision models and large language models (LLMs). Since these components…
As scaling up training data has significantly improved the general multimodal capabilities of Large Vision-Language Models (LVLMs), they still suffer from the hallucination issue, generating text that is inconsistent with the visual input.…