Language

2020

Citations in the corpus

Artificial cognition for social human-robot interaction: An implementation (2017, background): “Memory has been studied at length in the cognitive psychology and neuro-psychology communities: the idea of short-term and long-term memory is due to Atkinson and Shi ﬀ rin [47]; Anderson [48] proposes to split memory into declarative (explicit) and procedural (implicit) memories; Tulving [49] organ”
Directional asymmetries in the morphology and phonology of words, with special reference to Bantu (2008, background): “" (Sapir 1921:67) Greenberg (1966:92) notes that languages can have both prefixes and suffixes, but goes on to say that there are more languages lacking the former than the latter: " As between prefixing and suffixing, there is a general predominance of suffixing.”
Making Retrieval-Augmented Language Models Robust to Irrelevant Context (2023, unknown): “A dominant approach for combating this issue has been Retrieval Augmented Language Models (RALMs), which incorporate a retrieval mechanism to reduce the need for storing information in the LLM parameters (Guu et al., 2020; Lewis et al., 2020b; Izacard et al., 2023; Rubin & Berant, 2023).”
DriveGPT4: Interpretable End-to-End Autonomous Driving Via Large Language Model (2023, background): “Among these works, only a few focus on autonomous driving-related tasks [44], [45], [46].”
The Pleasures and Perils of Darwinizing Culture (with Phylogenies) (2007, background): “There is a saying in dialectology that, “every word has its own history” (Bloomfield 1935: 328).”
xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval (2023, methodology): “…models (Chen et al., 2021; Izadi et al., 2022; Nijkamp et al., 2022) and encoder-decoder models (Wang et al., 2021; Guo et al., 2022; Ahmad et al., 2021a) Notably, PaLM (Chowdhery et al., 2022) and AlphaCode (Li et al., 2022) outperform average human participant in competition-level coding.”
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities (2024, background): “Others have focused specifically on spatial reasoning as a task, answering questions about object spatial relations (e.g., above, below, left, right) in real [42, 52] or simulated [33] scenes.”
Large Language Model based Multi-Agents: A Survey of Progress and Challenges (2024, unknown): “[ Chen et al. , 2023b ] proposes an LLM-based consensus-seeking framework, which can be applied as a co-operative planner to a multi-robot aggregation task.”
Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack (2024, unknown): “Most LLMs are safety-aligned [8,15,19,25], meaning they are trained to avoid performing illegal or unethical tasks or generating harmful content in general.”
Willingness to Communicate in the Second Language: Understanding the Decision to Speak as a Volitional Process (2007, methodology): “Once the research participants were in the lab, they were asked to decide whether or not to engage in specific oral and written communication tasks (similar to the well-known Can Do tasks, see Clark, 1981) that were either easy or difficult.”