Misinformation regarding climate change is a key roadblock in addressing one of the most serious threats to humanity. This paper investigates factual accuracy in large language models (LLMs) regarding climate information. Using true/false labeled Q&A data for fine-tuning and evaluating LLMs on climate-related claims, we compare open-source models, assessing their ability to generate truthful responses to climate change questions. We investigate the detectability of models intentionally poisoned with false climate information, finding that such poisoning may not affect the accuracy of a model's responses in other domains. Furthermore, we compare the effectiveness of unlearning algorithms, fine-tuning, and Retrieval-Augmented Generation (RAG) for factually grounding LLMs on climate change topics. Our evaluation reveals that unlearning algorithms can be effective for nuanced conceptual claims, despite previous findings suggesting their inefficacy in privacy contexts. These insights aim to guide the development of more factually reliable LLMs and highlight the need for additional work to secure LLMs against misinformation attacks.

Recent works have extended notions of feature importance to \emph{semantic concepts} that are inherently interpretable to the users interacting with a black-box predictive model. Yet, precise statistical guarantees, such as false positive rate control, are needed to communicate findings transparently and to avoid unintended consequences in real-world scenarios. In this paper, we formalize the global (i.e., over a population) and local (i.e., for a sample) statistical importance of semantic concepts for the predictions of opaque models, by means of conditional independence, which allows for rigorous testing. We use recent ideas of sequential kernelized testing (SKIT) to induce a rank of importance across concepts, and showcase the effectiveness and flexibility of our framework on synthetic datasets as well as on image classification tasks using vision-language models such as CLIP.

Sony has revealed the lineup of games PlayStation Plus members can add to their library in June. For the first time, players will have access to PS VR2 titles through the Premium plan. First up, subscribers on all tiers will be able to claim SpongeBob Squarepants: The Cosmic Shake, Streets of Rage 4 and the solid wrestling game AEW Fight Forever starting on June 4 and retain access as long as their PS Plus membership stays active. Those with a Premium plan and a PS VR2 headset will be able to play Ghostbusters: Rise of the Ghost Lord, Walkabout Mini Golf, Synth Riders, Before Your Eyes and The Walking Dead: Saints & Sinners – Chapters 1 & 2 at no extra cost starting on June 6. Premium members can also dive into PS2 games Tomb Raider Legend, Star Wars: The Clone Wars and Sly Cooper and the Thievius Raccoonus starting on June 11. In addition, Sony will gradually bring more offerings to the PS Plus Catalog for Extra and Premium members over the coming weeks.

It has been lightly edited. When a young Chinese man sat down at his QWERTY keyboard in 2013 and rattled off an enigmatic string of letters and numbers, his forty-four keystrokes marked the first steps in a process known as "input" or shuru. Shuru is the act of getting Chinese characters to appear on a computer monitor or other digital device using a QWERTY keyboard or trackpad. The young man, Huang Zhenyu, was one of around 60 contestants in the 2013 National Chinese Characters Typing Competition. But Zhenyu's prizewinning performance wasn't solely noteworthy for his impressive typing speed--one of the fastest ever recorded.

As one of the most enduring metaphors within legal discourse, the marketplace of ideas has wielded considerable influence over the jurisprudential landscape for decades. A century after the inception of this theory, ChatGPT emerged as a revolutionary technological advancement in the twenty-first century. This research finds that ChatGPT effectively manifests the marketplace metaphor. It not only instantiates the promises envisaged by generations of legal scholars but also lays bare the perils discerned through sustained academic critique. Specifically, the workings of ChatGPT and the marketplace of ideas theory exhibit at least four common features: arena, means, objectives, and flaws. These shared attributes are sufficient to render ChatGPT historically the most qualified engine for actualizing the marketplace of ideas theory. The comparison of the marketplace theory and ChatGPT merely marks a starting point. A more meaningful undertaking entails reevaluating and reframing both internal and external AI policies by referring to the accumulated experience, insights, and suggestions researchers have raised to fix the marketplace theory. Here, a pivotal issue is: should truth-seeking be set as the goal of AI content governance? Given the unattainability of the absolute truth-seeking goal, I argue against adopting zero-risk policies. Instead, a more judicious approach would be to embrace a knowledge-based alternative wherein large language models (LLMs) are trained to generate competing and divergent viewpoints based on sufficient justifications. This research also argues that so-called AI content risks are not created by AI companies but are inherent in the entire information ecosystem. Thus, the burden of managing these risks should be distributed among different social actors, rather than being solely shouldered by chatbot companies.

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial computational resources and may significantly affect the utility of the original LLM. Recent endeavors have introduced more lightweight strategies, focusing on extracting "steering vectors" to guide the model's output toward desired behaviors by adjusting activations within specific layers of the LLM's transformer architecture. However, such steering vectors are directly extracted from the activations of human preference data and thus often lead to suboptimal results and occasional failures, especially in alignment-related scenarios. This work proposes an innovative approach that could produce more effective steering vectors through bi-directional preference optimization. Our method is designed to allow steering vectors to directly influence the generation probability of contrastive human preference data pairs, thereby offering a more precise representation of the target behavior. By carefully adjusting the direction and magnitude of the steering vector, we enabled personalized control over the desired behavior across a spectrum of intensities. Extensive experimentation across various open-ended generation tasks, particularly focusing on steering AI personas, has validated the efficacy of our approach. Moreover, we comprehensively investigate critical alignment-concerning scenarios, such as managing truthfulness, mitigating hallucination, and addressing jailbreaking attacks. Remarkably, our method can still demonstrate outstanding steering effectiveness across these scenarios. Furthermore, we showcase the transferability of our steering vectors across different models/LoRAs and highlight the synergistic benefits of applying multiple vectors simultaneously.

Retrieval Augmented Generation (RAG) has greatly improved the performance of Large Language Model (LLM) responses by grounding generation with context from existing documents. These systems work well when documents are clearly relevant to a question context. But what about when a document has partial information, or less obvious connections to the context? And how should we reason about connections between documents? In this work, we seek to answer these two core questions about RAG generation. We introduce G-RAG, a reranker based on graph neural networks (GNNs) between the retriever and reader in RAG. Our method combines both connections between documents and semantic information (via Abstract Meaning Representation graphs) to provide a context-informed ranker for RAG. G-RAG outperforms state-of-the-art approaches while having smaller computational footprint. Additionally, we assess the performance of PaLM 2 as a reranker and find it to significantly underperform G-RAG. This result emphasizes the importance of reranking for RAG even when using Large Language Models.

Experts in various fields routinely perform methodical writing tasks to plan, organize, and report their work. From a clinician writing a differential diagnosis for a patient, to a teacher writing a lesson plan for students, these tasks are pervasive, requiring to methodically generate structured long-form output for a given input. We develop a typology of methodical tasks structured in the form of a task objective, procedure, input, and output, and introduce DoLoMiTes, a novel benchmark with specifications for 519 such tasks elicited from hundreds of experts from across 25 fields. Our benchmark further contains specific instantiations of methodical tasks with concrete input and output examples (1,857 in total) which we obtain by collecting expert revisions of up to 10 model-generated examples of each task. We use these examples to evaluate contemporary language models highlighting that automating methodical tasks is a challenging long-form generation problem, as it requires performing complex inferences, while drawing upon the given context as well as domain knowledge.

While Large Language Models (LLMs) can serve as agents to simulate human behaviors (i.e., role-playing agents), we emphasize the importance of point-in-time role-playing. This situates characters at specific moments in the narrative progression for three main reasons: (i) enhancing users' narrative immersion, (ii) avoiding spoilers, and (iii) fostering engagement in fandom role-playing. To accurately represent characters at specific time points, agents must avoid character hallucination, where they display knowledge that contradicts their characters' identities and historical timelines. We introduce TimeChara, a new benchmark designed to evaluate point-in-time character hallucination in role-playing LLMs. Comprising 10,895 instances generated through an automated pipeline, this benchmark reveals significant hallucination issues in current state-of-the-art LLMs (e.g., GPT-4o). To counter this challenge, we propose Narrative-Experts, a method that decomposes the reasoning steps and utilizes narrative experts to reduce point-in-time character hallucinations effectively. Still, our findings with TimeChara highlight the ongoing challenges of point-in-time character hallucination, calling for further study.

With the enhancement in the field of generative artificial intelligence (AI), contextual question answering has become extremely relevant. Attributing model generations to the input source document is essential to ensure trustworthiness and reliability. We observe that when large language models (LLMs) are used for contextual question answering, the output answer often consists of text copied verbatim from the input prompt which is linked together with "glue text" generated by the LLM. Motivated by this, we propose that LLMs have an inherent awareness from where the text was copied, likely captured in the hidden states of the LLM. We introduce a novel method for attribution in contextual question answering, leveraging the hidden state representations of LLMs. Our approach bypasses the need for extensive model retraining and retrieval model overhead, offering granular attributions and preserving the quality of generated answers. Our experimental results demonstrate that our method performs on par or better than GPT-4 at identifying verbatim copied segments in LLM generations and in attributing these segments to their source. Importantly, our method shows robust performance across various LLM architectures, highlighting its broad applicability. Additionally, we present Verifiability-granular, an attribution dataset which has token level annotations for LLM generations in the contextual question answering setup.