Related papers: Omission Constraints Decay While Commission Constr…

Can large language models (LLMs) generate continuous numerical features that improve reinforcement learning (RL) trading agents? We build a modular pipeline where a frozen LLM serves as a stateless feature extractor, transforming…

Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare. However, their ability to produce deceptive outputs, whether intentionally or inadvertently, poses…

Large Language Models (LLMs) often struggle to use information across long inputs effectively. Prior work has identified positional biases, such as the Lost in the Middle (LiM) effect, where models perform better when information appears at…

Abstention, the refusal of large language models (LLMs) to provide an answer, is increasingly recognized for its potential to mitigate hallucinations and enhance safety in LLM systems. In this survey, we introduce a framework to examine…

Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer). This weakness is even evident in temporal question answering, where models frequently…

Large language model (LLM) agents show promise in an increasing number of domains. In many proposed applications, it is expected that the agent reasons over accumulated experience presented in an input prompt. We propose the OEDD…

Power differences shape human communication through well documented socio cognitive effects, including language coordination, pronoun usage, authority bias, and harmful compliance. We examine whether large language models (LLMs) exhibit…

Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support. This gap is commonly attributed to retrieval failures -- the models' inability to identify…

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts. Recent works like Recursive Language…

LLM-powered coding agents suffer from a poorly understood failure mode we term output stalling: the agent silently produces empty responses when attempting to generate large, format-heavy documents. We present a theoretical framework that…

When multiple LLM-based code agents independently implement parts of the same class, they must agree on shared internal representations, even when the specification leaves those choices implicit. We study this coordination problem across 51…

To combat the misuse of Large Language Models (LLMs), many recent studies have presented LLM-generated-text detectors with promising performance. When users instruct LLMs to generate texts, the instruction can include different constraints…

Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptive…

Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…

LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be correct. While most abstention methods decide to withhold…

Multi-turn tool-calling LLMs (models capable of invoking external APIs or tools across several user turns) have emerged as a key feature in modern AI assistants, enabling extended dialogues from benign tasks to critical business, medical,…

Large language models (LLMs) can exhibit concept-conditioned semantic divergence: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like responses that evade token-trigger audits. This behavior falls…

The widespread adoption of open-source software (OSS) has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models…

Large Language Models (LLMs) generate text token-by-token in discrete time, yet real-world communication, from therapy sessions to business negotiations, critically depends on continuous time constraints. Current LLM architectures and…