Related papers: Amortizing Pragmatic Program Synthesis with Rankin…
We introduce SLR, an end-to-end framework for systematic evaluation and training of Large Language Models (LLMs) via Scalable Logical Reasoning. Given a user's task specification, SLR automatically synthesizes (i) an instruction prompt for…
High-quality data is essential for conversational recommendation systems and serves as the cornerstone of the network architecture development and training strategy design. Existing works contribute heavy human efforts to manually labeling…
We present new techniques for automatically constructing probabilistic programs for data analysis, interpretation, and prediction. These techniques work with probabilistic domain-specific data modeling languages that capture key properties…
Logical reasoning remains a challenge for natural language processing, but it can be improved by training language models to mimic theorem provers on procedurally generated problems. Previous work used domain-specific proof generation…
When faced with novel situations, people are able to marshal relevant considerations from a wide range of background knowledge and put these to use in inferences and predictions. What permits us to draw in globally relevant information and…
Multimodal program synthesis, which leverages different types of user input to synthesize a desired program, is an attractive way to scale program synthesis to challenging settings; however, it requires integrating noisy signals from the…
We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly leverages test inputs during synthesis. While prior approaches to program synthesis--whether based on natural language descriptions…
Conflict-free replicated data types (CRDTs) are a promising tool for designing scalable, coordination-free distributed systems. However, constructing correct CRDTs is difficult, posing a challenge for even seasoned developers. As a result,…
We present a tractable method for synthesizing arbitrarily large concurrent programs, for a shared memory model with common hardware-available primitives such as atomic registers, compare-and-swap, load-linked/store conditional, etc. The…
The process of rank aggregation is intimately intertwined with the structure of skew-symmetric matrices. We apply recent advances in the theory and algorithms of matrix completion to skew-symmetric matrices. This combination of ideas…
Synthetic data augmentation helps language models learn new knowledge in data-constrained domains. However, naively scaling existing synthetic data methods by training on more synthetic tokens or using stronger generators yields diminishing…
Argumentation is a very active research field of Artificial Intelligence concerned with the representation and evaluation of arguments used in dialogues between humans and/or artificial agents. Acceptability semantics of formal…
Automated Scoring (AS), the natural language processing task of scoring essays and speeches in an educational testing setting, is growing in popularity and being deployed across contexts from government examinations to companies providing…
Programming-by-example (PBE) is a synthesis paradigm that allows users to generate functions by simply providing input-output examples. While a promising interaction paradigm, synthesis is still too slow for realtime interaction and more…
When fine-tuning pre-trained Language Models (LMs) to exhibit desired behaviors, maintaining control over risk is critical for ensuring both safety and trustworthiness. Most existing safety alignment methods, such as Safe RLHF and SACPO,…
Language models (LMs) that jointly generate end-task answers as well as free-text rationales are known as self-rationalization models. Recent works demonstrate great performance gain for self-rationalization by few-shot prompting LMs with…
We introduce a new class of distributed algorithms for the approximate consensus problem in dynamic rooted networks, which we call amortized averaging algorithms. They are deduced from ordinary averaging algorithms by adding a…
Being a fully automated technique for resource analysis, automatic amortized resource analysis (AARA) can fail in returning worst-case cost bounds of programs, fundamentally due to the undecidability of resource analysis. For programmers…
Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning. While such an approach works well for tasks that only require forward…
The automatic generation of computer programs is one of the main applications with practical relevance in the field of evolutionary computation. With program synthesis techniques not only software developers could be supported in their…