A core part of scientific peer review involves providing expert critiques that directly assess the scientific claims a paper makes. While it is now possible to automatically generate plausible (if generic) reviews, ensuring that these reviews are sound and grounded in the papers' claims remains challenging. To facilitate LLM benchmarking on these challenges, we introduce CLAIMCHECK, an annotated dataset of NeurIPS 2023 and 2024 submissions and reviews mined from OpenReview. CLAIMCHECK is richly annotated by ML experts for weakness statements in the reviews and the paper claims that they dispute, as well as fine-grained labels of the validity, objectivity, and type of the identified weaknesses. We benchmark several LLMs on three claim-centric tasks supported by CLAIMCHECK, requiring models to (1) associate weaknesses with the claims they dispute, (2) predict fine-grained labels for weaknesses and rewrite the weaknesses to enhance their specificity, and (3) verify a paper's claims with grounded reasoning. Our experiments reveal that cutting-edge LLMs, while capable of predicting weakness labels in (2), continue to underperform relative to human experts on all other tasks.

AI systems make decisions in physical environments through primitive actions or affordances that are accessed via API calls. While deploying AI agents in the real world involves numerous high-level actions, existing embodied simulators offer a limited set of domain-salient APIs. This naturally brings up the questions: how many primitive actions (APIs) are needed for a versatile embodied agent, and what should they look like? We explore this via a thought experiment: assuming that wikiHow tutorials cover a wide variety of human-written tasks, what is the space of APIs needed to cover these instructions? We propose a framework to iteratively induce new APIs by grounding wikiHow instruction to situated agent policies. Inspired by recent successes in large language models (LLMs) for embodied planning, we propose a few-shot prompting to steer GPT-4 to generate Pythonic programs as agent policies and bootstrap a universe of APIs by 1) reusing a seed set of APIs; and then 2) fabricate new API calls when necessary. The focus of this thought experiment is on defining these APIs rather than their executability. We apply the proposed pipeline on instructions from wikiHow tutorials. On a small fraction (0.5%) of tutorials, we induce an action space of 300+ APIs necessary for capturing the rich variety of tasks in the physical world. A detailed automatic and human analysis of the induction output reveals that the proposed pipeline enables effective reuse and creation of APIs. Moreover, a manual review revealed that existing simulators support only a small subset of the induced APIs (9 of the top 50 frequent APIs), motivating the development of action-rich embodied environments.

We propose a simple yet effective and robust method for contrastive captioning: generating discriminative captions that distinguish target images from very similar alternative distractor images. Our approach is built on a pragmatic inference procedure that formulates captioning as a reference game between a speaker, which produces possible captions describing the target, and a listener, which selects the target given the caption. Unlike previous methods that derive both speaker and listener distributions from a single captioning model, we leverage an off-the-shelf CLIP model to parameterize the listener. Compared with captioner-only pragmatic models, our method benefits from rich vision language alignment representations from CLIP when reasoning over distractors. Like previous methods for discriminative captioning, our method uses a hyperparameter to control the tradeoff between the informativity (how likely captions are to allow a human listener to discriminate the target image) and the fluency of the captions. However, we find that our method is substantially more robust to the value of this hyperparameter than past methods, which allows us to automatically optimize the captions for informativity - outperforming past methods for discriminative captioning by 11% to 15% accuracy in human evaluations

Event grounding aims at linking mention references in text corpora to events from a knowledge base (KB). Previous work on this task focused primarily on linking to a single KB event, thereby overlooking the hierarchical aspects of events. Events in documents are typically described at various levels of spatio-temporal granularity (Glavas et al. 2014). These hierarchical relations are utilized in downstream tasks of narrative understanding and schema construction. In this work, we present an extension to the event grounding task that requires tackling hierarchical event structures from the KB. Our proposed task involves linking a mention reference to a set of event labels from a subevent hierarchy in the KB. We propose a retrieval methodology that leverages event hierarchy through an auxiliary hierarchical loss (Murty et al. 2018). On an automatically created multilingual dataset from Wikipedia and Wikidata, our experiments demonstrate the effectiveness of the hierarchical loss against retrieve and re-rank baselines (Wu et al. 2020; Pratapa, Gupta, and Mitamura 2022). Furthermore, we demonstrate the systems' ability to aid hierarchical discovery among unseen events.

Commonsense knowledge acquisition and reasoning have long been a core artificial intelligence problem. However, in the past, there has been a lack of scalable methods to collect commonsense knowledge. In this paper, we propose to develop principles for collecting commonsense knowledge based on selectional preference. We generalize the definition of selectional preference from one-hop linguistic syntactic relations to higher-order relations over linguistic graphs. Unlike previous commonsense knowledge definition (e.g., ConceptNet), the selectional preference (SP) knowledge only relies on statistical distribution over linguistic graphs, which can be efficiently and accurately acquired from the unlabeled corpus with modern tools. Following this principle, we develop a large-scale eventuality (a linguistic term covering activity, state, and event)-based knowledge graph ASER, where each eventuality is represented as a dependency graph, and the relation between them is a discourse relation defined in shallow discourse parsing. The higher-order selectional preference over collected linguistic graphs reflects various kinds of commonsense knowledge. Moreover, motivated by the observation that humans understand events by abstracting the observed events to a higher level and can thus transferring their knowledge to new events, we propose a conceptualization module to significantly boost the coverage of ASER. In total, ASER contains 438 million eventualities and 648 million edges between eventualities. After conceptualization with Probase, a selectional preference based concept-instance relational knowledge base, our concept graph contains 15 million conceptualized eventualities and 224 million edges between them. Detailed analysis is provided to demonstrate its quality. All the collected data, APIs, and tools are available at https://github.com/HKUST-KnowComp/ASER.