7 citations · 14 across the 13 of their papers we have counts for
15 papers
Do VLAs Understand and Adapt to the Objects They Handle, or Simply Replay Learned Behaviors?
Xinnuo Xu
This paper asks whether VLA generalization is grounded in a global understanding of objects' physical properties that enables policies to adapt their motion to unseen setups, or if…
Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed
Xinnuo Xu, Anja Thieme, Daniela Massiceti +6
State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety guidelines to all users. Our emp…
Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency
Victoria Lin, Xinnuo Xu, Rachel Lawrence +4
Despite their strong performance on reasoning benchmarks, large language models (LLMs) have proven brittle when presented with counterfactual questions, suggesting weaknesses in th…
RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation
Xinnuo Xu, Rachel Lawrence, Kshitij Dubey +7
Recent Large Language Models (LLMs) have reported high accuracy on reasoning benchmarks. However, it is still unclear whether the observed results arise from true reasoning or from…
Synthetic Function Demonstrations Improve Generation in Low-Resource Programming Languages
Nick McKenna, Xinnuo Xu, Jack Williams +3
A key consideration when training an LLM is whether the target language is more or less resourced, for example English compared to Welsh, or Python compared to Excel. Typical train…
Compositional Causal Reasoning Evaluation in Language Models
Jacqueline R. M. A. Maasch, Alihan Hüyük, Xinnuo Xu +2
Causal reasoning and compositional reasoning are two core aspirations in AI. Measuring the extent of these behaviors requires principled evaluation methods. We explore a unified pe…
A Bayesian Approach to Data Point Selection
Xinnuo Xu, Minyoung Kim, Royson Lee +2
Data point selection (DPS) is becoming a critical topic in deep learning due to the ease of acquiring uncurated training data compared to the difficulty of obtaining curated or pro…
Reasoning Elicitation in Language Models via Counterfactual Feedback
Alihan Hüyük, Xinnuo Xu, Jacqueline Maasch +2
Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answeri…
Graph Guided Question Answer Generation for Procedural Question-Answering
Hai X. Pham, Isma Hadji, Xinnuo Xu +6
In this paper, we focus on task-specific question answering (QA). To this end, we introduce a method for generating exhaustive and high-quality training data, which allows us to tr…
Compositional Generalization for Data-to-Text Generation
Xinnuo Xu, Ivan Titov, Mirella Lapata
Data-to-text generation involves transforming structured data, often represented as predicate-argument tuples, into coherent textual descriptions. Despite recent advances, systems…
MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization
Xinnuo Xu, Ondřej Dušek, Shashi Narayan +2
One of the most challenging aspects of current single-document news summarization is that the summary often contains 'extrinsic hallucinations', i.e., facts that are not present in…
AGGGEN: Ordering and Aggregating while Generating
Xinnuo Xu, Ondřej Dušek, Verena Rieser +1
We present AGGGEN (pronounced 'again'), a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input ag…
AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation
Xinnuo Xu, Guoyin Wang, Young-Bum Kim +1
Natural Language Generation (NLG) is a key component in a task-oriented dialogue system, which converts the structured meaning representation (MR) to the natural language. For larg…
Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity
Xinnuo Xu, Ondřej Dušek, Ioannis Konstas +1
We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1)…
An Ensemble Model with Ranking for Social Dialogue
Ioannis Papaioannou, Amanda Cercas Curry, Jose L. Part +6
Open-domain social dialogue is one of the long-standing goals of Artificial Intelligence. This year, the Amazon Alexa Prize challenge was announced for the first time, where real c…