Related papers: Sleeping Beauty Reconsidered: Conditioning and Ref…
The problem of mirror-reflection symmetry (MRS) and time-reversal symmetry (TRS) in our world is discussed. The opinion is expressed, that well-known experiments on parity violation and CP-violation can be treated as signals of some new,…
Existing color sampling based alpha matting methods use the compositing equation to estimate alpha at a pixel from pairs of foreground (F) and background (B) samples. The quality of the matte depends on the selected (F,B) pairs. In this…
Synchronisation and pattern formation have been intensely addressed for systems evolving on static networks. Extending the study to include the inherent ability of the network to adjust over time proved cumbersome and led to conclusions…
Contemporary face hallucination (FH) models exhibit considerable ability to reconstruct high-resolution (HR) details from low-resolution (LR) face images. This ability is commonly learned from examples of corresponding HR-LR image pairs,…
Large language models are prone to hallucinating factually incorrect statements. A key source of these errors is exposure to new factual information through supervised fine-tuning (SFT), which can increase hallucinations w.r.t. knowledge…
This paper studies causal discovery in irregularly sampled time series-a key challenge in risk-sensitive domains like finance, healthcare, and climate science, where missing data and inconsistent sampling frequencies distort causal…
This paper explores hallucination phenomena in large language models (LLMs) through the lens of language philosophy and psychoanalysis. By incorporating Lacan's concepts of the "chain of signifiers" and "suture points," we propose the…
Hallucination is a central failure mode in large language models (LLMs). We focus on hallucinations of answers to questions like: "Which instrument did Glenn Gould play?", but we ask these questions for synthetic entities that are unknown…
Hallucinations in Large Language Models (LLMs) -- generations that are plausible but factually unfaithful -- remain a critical barrier to high-stakes deployment. Current detection methods typically rely on computationally expensive external…
Large language models increasingly rely on synthetic data due to human-written content scarcity, yet recursive training on model-generated outputs leads to model collapse, a degenerative process threatening factual reliability. We define…
Fine-tuning pre-trained transformer-based language models such as BERT has become a common practice dominating leaderboards across various NLP benchmarks. Despite the strong empirical performance of fine-tuned models, fine-tuning is an…
Hallucination in large language models (LLMs) is a fundamental challenge, particularly in open-domain question answering. Prior work attempts to detect hallucination with model-internal signals such as token-level entropy or generation…
This paper explores the challenges of constructing suitable inferential models in scenarios where the parameter of interest is determined in light of the data, such as regression after variable selection. Two compelling arguments for…
Feedback optimization has emerged as an effective strategy for steady-state optimization of dynamical systems. By exploiting models of the steady-state input-output sensitivity, methods of this type are often sample efficient, and their use…
For Large Language Models (LLMs) to be reliably deployed, models must effectively know when not to answer: abstain. Reasoning models, in particular, have gained attention for impressive performance on complex tasks. However, reasoning…
Software is now ubiquitous and involved in complex interactions with the human users and the physical world in so-called cyber-physical systems where the management of time is a major issue. Separation of concerns is a key asset in the…
Detecting content that contradicts or is unsupported by a given source text is a critical challenge for the safe deployment of generative language models. We introduce HALT-RAG, a post-hoc verification system designed to identify…
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…
Detecting hallucinations in large language models (LLMs) remains a fundamental challenge for their trustworthy deployment. Going beyond basic uncertainty-driven hallucination detection frameworks, we propose a simple yet powerful method…
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…