相关论文: Instruction Complexity Induces Positional Collapse…

Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled…

Language models are trained to follow instructions, but they are also powerful pattern completers. What happens when these two objectives conflict? We construct conversations in which a user instruction to behave in a target way T (e.g.,…

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed. However, we reveal a counterintuitive phenomenon: instruction following can…

Annotation automation via Large Language Models (LLMs) is the core approach for scaling NLP datasets; however, LLM behavior with respect to closed-set instructions in low-resource languages has not been well studied. We present MultiSoc-4D,…

Real-world instructions with multiple constraints pose a significant challenge to existing large language models (LLMs). An observation is that the LLMs exhibit dramatic performance fluctuation when disturbing the order of the incorporated…

Despite growing interest in using Large Language Models (LLMs) for educational assessment, it remains unclear how closely they align with human scoring. We present a systematic evaluation of instruction-tuned LLMs across three open…

This study examines how user-provided suggestions affect Large Language Models (LLMs) in a simulated educational context, where sycophancy poses significant risks. Testing five different LLMs from the OpenAI GPT-4o and GPT-4.1 model classes…

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Numerous studies have shown that multimodal LLMs process speech and images well but fail in non-intuitive ways rendering trivial tasks such as object counting unreliable. We investigate this behavior from an information-theoretic…

Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful. Nevertheless, some human instructions are often malicious or misleading and…

Large Language Models (LLMs) exhibit position bias systematically underweighting information based on its location in the context but how this bias varies across languages and models remains unclear. We conduct a multilingual study across…

Instruction tuning has emerged as a paramount method for tailoring the behaviors of LLMs. Recent work has unveiled the potential for LLMs to achieve high performance through fine-tuning with a limited quantity of high-quality instruction…

Large Language Models (LLMs) exhibit catastrophic performance degradation when processing contexts approaching certain critical thresholds, even when information remains relevant. This intelligence degradation-defined as over 30% drop in…

The design of safety-critical agents based on large language models (LLMs) requires more than simple prompt engineering. This paper presents a comprehensive information-theoretic analysis of how rule encodings in system prompts influence…

The extraordinary capabilities of large language models (LLMs) such as ChatGPT and GPT-4 are in part unleashed by aligning them with reward models that are trained on human preferences, which are often represented as rankings of responses…

Instruction-tuned large language models (IT-LLMs) exhibit strong zero-shot reasoning, yet their ability to execute simple, self-contained instructions remains underexplored, despite this being foundational to complex instruction-following.…

Large Language Model (LLM)-powered multi-agent systems (MAS) have rapidly advanced collaborative reasoning, tool use, and role-specialized coordination in complex tasks. However, reliability-critical deployment remains hindered by a…

Structured width pruning of GLU-MLP layers, guided by the Maximum Absolute Weight (MAW) criterion, reveals a systematic dichotomy in how reducing the expansion ratio affects different model capabilities. While performance on tasks relying…

Despite significant achievements in improving the instruction-following capabilities of large language models (LLMs), the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge.…