Related papers: Non-Halting Queries: Exploiting Fixed Points in LL…
As large language models (LLMs) advance, ensuring AI safety and alignment is paramount. One popular approach is prompt guards, lightweight mechanisms designed to filter malicious queries while being easy to implement and update. In this…
One of the most impressive results of recent NLP history is the ability of pre-trained language models to solve new tasks in a zero-shot setting. To achieve this, NLP tasks are framed as natural language prompts, generating a response…
Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially -- first to produce intermediate results and then the final answer. However, using these methods, both decoder and model are…
Prompt-based learning is susceptible to intrinsic bias present in pre-trained language models (LMs), leading to sub-optimal performance in prompt-based zero/few-shot settings. In this work, we propose a null-input prompting method to…
We systematically evaluate the reproducibility of data analysis conducted by Large Language Models (LLMs). We evaluate two prompting strategies, six models, and four temperature settings, with ten independent executions per configuration,…
Consistently scaling pre-trained language models (PLMs) imposes substantial burdens on model adaptation, necessitating more efficient alternatives to conventional fine-tuning. Given the advantage of prompting in the zero-shot setting and…
Large Language Models (LLMs), including GPT-3.5, LLaMA, and PaLM, seem to be knowledgeable and able to adapt to many tasks. However, we still cannot completely trust their answers, since LLMs suffer from \textbf{hallucination}\textemdash…
We introduce fidelity probes: natural-language questions generated from a reference artifact with code-derived ground-truth answers, answered from a candidate specification. The fraction of agreeing probes, which we call the fidelity,…
An LLM's factuality and refusal training can be compromised by simple changes to a prompt. Models often adopt user beliefs (sycophancy) or satisfy inappropriate requests which are wrapped within special text (jailbreaking). We explore…
Wu et al. (2026) showed that most frontier large language models (LLMs) recommend a sponsored, roughly twice-as-expensive flight when their system prompt contains a soft sponsorship cue. We reproduce their evaluation on ten open-weight chat…
Recent advances in reasoning with large language models (LLMs) have demonstrated strong performance on complex mathematical tasks, including combinatorial optimization. Techniques such as Chain-of-Thought and In-Context Learning have…
The remarkable advancements in Multimodal Large Language Models (MLLMs) have not rendered them immune to challenges, particularly in the context of handling deceptive information in prompts, thus producing hallucinated responses under such…
Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API calls with increasingly large context windows. However,…
In large language models (LLM)-based recommendation systems (LLM-RSs), accurately predicting user preferences by leveraging the general knowledge of LLMs is possible without requiring extensive training data. By converting recommendation…
Large Language Models (LLMs), despite their impressive capabilities, often fail to accurately repeat a single word when prompted to, and instead output unrelated text. This unexplained failure mode represents a vulnerability, allowing even…
Chain-of-Thought (CoT) prompting has improved the reasoning performance of large language models (LLMs), but it remains unclear why it works and whether it is the unique mechanism for triggering reasoning in large language models. In this…
Using tools by Large Language Models (LLMs) is a promising avenue to extend their reach beyond language or conversational settings. The number of tools can scale to thousands as they enable accessing sensory information, fetching updated…
Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…
This paper presents null-shot prompting. Null-shot prompting exploits hallucination in large language models (LLMs) by instructing LLMs to utilize information from the "Examples" section that never exists within the provided context to…
Large Language Models prompting, such as using in-context demonstrations, is a mainstream technique for invoking LLMs to perform high-performance and solid complex reasoning (e.g., mathematical reasoning, commonsense reasoning), and has the…