Coding assistants are increasingly leveraged in game design, both generating code and making high-level plans. To what degree can these tools align with developer workflows, and what new modes of human-computer interaction can emerge from their use? We present DreamGarden, an AI system capable of assisting with the development of diverse game environments in Unreal Engine. At the core of our method is an LLM-driven planner, capable of breaking down a single, high-level prompt -- a dream, memory, or imagined scenario provided by a human user -- into a hierarchical action plan, which is then distributed across specialized submodules facilitating concrete implementation. This system is presented to the user as a garden of plans and actions, both growing independently and responding to user intervention via seed prompts, pruning, and feedback. Through a user study, we explore design implications of this system, charting courses for future work in semi-autonomous assistants and open-ended simulation design.

Large Language Models (LLMs) have shown promising performance in code generation. However, how to reliably evaluate code generated by LLMs remains an unresolved problem. This paper presents CodeJudge, a code evaluation framework that leverages LLMs to evaluate the semantic correctness of generated code without the need for test cases. We investigate different ways to guide the LLM in performing "slow thinking" to arrive at an in-depth and reliable evaluation. We experimented with four LLMs as evaluators on four code generation datasets and five programming languages. The results show that CodeJudge significantly outperformed existing methods in most settings. Furthermore, compared with a SOTA GPT-3.5-based code evaluation method, CodeJudge achieved better results even when using a much smaller model, Llama-3-8B-Instruct. Our code and datasets are available on GitHub https://github.com/VichyTong/CodeJudge.

Deploying large language models in production requires simultaneous attention to efficiency and risk control. Prior work has shown the possibility to cut costs while maintaining similar accuracy, but has neglected to focus on risk control. By contrast, here we present hierarchical chains with multi-level abstention (HCMA), which use model-intrinsic uncertainty to delegate queries along the LLM intelligence hierarchy, enabling training-free model switching based solely on black-box API calls. Our framework presents novel trade-offs between efficiency and risk. For example, deploying HCMA on MMLU cuts the error rate of Llama3 405B by 30% when the model is allowed to abstain on 20% of the queries. To calibrate HCMA for optimal performance, our approach uses data-efficient logistic regressions (based on a simple nonlinear feature transformation), which require only 50 or 100 labeled examples to achieve excellent calibration error (ECE), cutting ECE by 50% compared to naive Platt scaling. On free-form generation tasks, we find that chain-of-thought is ineffectual for selective prediction, whereas zero-shot prompting drives error to 0% on TruthfulQA at high abstention rates. As LLMs are increasingly deployed across computing environments with different capabilities (such as mobile, laptop, and cloud), our framework paves the way towards maintaining deployment efficiency while putting in place sharp risk controls.

Open-ended short-answer questions (SAGs) have been widely recognized as a powerful tool for providing deeper insights into learners' responses in the context of learning analytics (LA). However, SAGs often present challenges in practice due to the high grading workload and concerns about inconsistent assessments. With recent advancements in natural language processing (NLP), automatic short-answer grading (ASAG) offers a promising solution to these challenges. Despite this, current ASAG algorithms are often limited in generalizability and tend to be tailored to specific questions. In this paper, we propose a unified multi-agent ASAG framework, GradeOpt, which leverages large language models (LLMs) as graders for SAGs. More importantly, GradeOpt incorporates two additional LLM-based agents - the reflector and the refiner - into the multi-agent system. This enables GradeOpt to automatically optimize the original grading guidelines by performing self-reflection on its errors. Through experiments on a challenging ASAG task, namely the grading of pedagogical content knowledge (PCK) and content knowledge (CK) questions, GradeOpt demonstrates superior performance in grading accuracy and behavior alignment with human graders compared to representative baselines. Finally, comprehensive ablation studies confirm the effectiveness of the individual components designed in GradeOpt.

Recent work showed that retrieval based on embedding similarity (e.g., for retrieval-augmented generation) is vulnerable to poisoning: an adversary can craft malicious documents that are retrieved in response to broad classes of queries. We demonstrate that previous, HotFlip-based techniques produce documents that are very easy to detect using perplexity filtering. Even if generation is constrained to produce low-perplexity text, the resulting documents are recognized as unnatural by LLMs and can be automatically filtered from the retrieval corpus. We design, implement, and evaluate a new controlled generation technique that combines an adversarial objective (embedding similarity) with a "naturalness" objective based on soft scores computed using an open-source, surrogate LLM. The resulting adversarial documents (1) cannot be automatically detected using perplexity filtering and/or other LLMs, except at the cost of significant false positives in the retrieval corpus, yet (2) achieve similar poisoning efficacy to easilydetectable documents generated using HotFlip, and (3) are significantly more effective than prior methods for energy-guided generation, such as COLD. Many modern retrieval systems use embeddings, i.e., dense vector representations, of documents and queries to enable retrieval based on semantic similarity. Chaudhari et al. (2024) and Zhong et al. (2023) recently demonstrated that an adversary can use HotFlip Ebrahimi et al. (2018) to generate documents whose embeddings have high similarity to, and will thus be retrieved in response to, broad classes of queries. We first demonstrate that adversarial documents produced by HotFlip have much higher perplexity than normal text and can be filtered out with negligible collateral damage (i.e., false positives).

The ability to plan a course of action that achieves a desired state of affairs has long been considered a core competence of intelligent agents and has been an integral part of AI research since its inception. With the advent of large language models (LLMs), there has been considerable interest in the question of whether or not they possess such planning abilities, but -- despite the slew of new private and open source LLMs since GPT3 -- progress has remained slow. OpenAI claims that their recent o1 (Strawberry) model has been specifically constructed and trained to escape the normal limitations of autoregressive LLMs -- making it a new kind of model: a Large Reasoning Model (LRM). In this paper, we evaluate the planning capabilities of two LRMs (o1-preview and o1-mini) on both planning and scheduling benchmarks. We see that while o1 does seem to offer significant improvements over autoregressive LLMs, this comes at a steep inference cost, while still failing to provide any guarantees over what it generates. We also show that combining o1 models with external verifiers -- in a so-called LRM-Modulo system -- guarantees the correctness of the combined system's output while further improving performance.

Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. This ability to extract training data can be problematic, for example, when data are private or sensitive. In this work, we investigate methods to mitigate memorization: three regularizer-based, three finetuning-based, and eleven machine unlearning-based methods, with five of the latter being new methods that we introduce. We also introduce TinyMem, a suite of small, computationally-efficient LMs for the rapid development and evaluation of memorization-mitigation methods. We demonstrate that the mitigation methods that we develop using TinyMem can successfully be applied to production-grade LMs, and we determine via experiment that: regularizer-based mitigation methods are slow and ineffective at curbing memorization; fine-tuning-based methods are effective at curbing memorization, but overly expensive, especially for retaining higher accuracies; and unlearning-based methods are faster and more effective, allowing for the precise localization and removal of memorized information from LM weights prior to inference. We show, in particular, that our proposed unlearning method BalancedSubnet outperforms other mitigation methods at removing memorized information while preserving performance on target tasks.

A major challenge for transformers is generalizing to sequences longer than those observed during training. While previous works have empirically shown that transformers can either succeed or fail at length generalization depending on the task, theoretical understanding of this phenomenon remains limited. In this work, we introduce a rigorous theoretical framework to analyze length generalization in causal transformers with learnable absolute positional encodings. In particular, we characterize those functions that are identifiable in the limit from sufficiently long inputs with absolute positional encodings under an idealized inference scheme using a norm-based regularizer. This enables us to prove the possibility of length generalization for a rich family of problems. We experimentally validate the theory as a predictor of success and failure of length generalization across a range of algorithmic and formal language tasks. Our theory not only explains a broad set of empirical observations but also opens the way to provably predicting length generalization capabilities in transformers.

In many domains, such as healthcare, time-series data is often irregularly sampled with varying intervals between observations. This poses challenges for classical time-series models that require equally spaced data. To address this, we propose a novel time-series Transformer called Trajectory Generative Pre-trained Transformer (TrajGPT). TrajGPT employs a novel Selective Recurrent Attention (SRA) mechanism, which utilizes a data-dependent decay to adaptively filter out irrelevant past information based on contexts. By interpreting TrajGPT as discretized ordinary differential equations (ODEs), it effectively captures the underlying continuous dynamics and enables time-specific inference for forecasting arbitrary target timesteps. Experimental results demonstrate that TrajGPT excels in trajectory forecasting, drug usage prediction, and phenotype classification without requiring task-specific fine-tuning. By evolving the learned continuous dynamics, TrajGPT can interpolate and extrapolate disease risk trajectories from partially-observed time series. The visualization of predicted health trajectories shows that TrajGPT forecasts unseen diseases based on the history of clinically relevant phenotypes (i.e., contexts). Time-series representation learning plays a crucial role in various domains, as it facilitates the extraction of generalizable temporal patterns from large-scale, unlabeled data, which can then be adapted for diverse tasks (Ma et al., 2023).

Post-training Large Language Models (LLMs) with explicit reasoning trajectories can enhance their reasoning abilities. However, acquiring such high-quality trajectory data typically demands meticulous supervision from humans or superior models, which can be either expensive or license-constrained. In this paper, we explore how far an LLM can improve its reasoning by self-synthesizing reasoning paths as training data without any additional supervision. Existing self-synthesizing methods, such as STaR, suffer from poor generalization to out-of-domain (OOD) reasoning tasks. We hypothesize it is due to that their self-synthesized reasoning paths are too task-specific, lacking general task-agnostic reasoning guidance. To address this, we propose Reasoning Generalist via Self-Improvement (ReGenesis), a method to self-synthesize reasoning paths as post-training data by progressing from abstract to concrete. More specifically, ReGenesis self-synthesizes reasoning paths by converting general reasoning guidelines into task-specific ones, generating reasoning structures, and subsequently transforming these structures into reasoning paths, without the need for human-designed task-specific examples used in existing methods. We show that ReGenesis achieves superior performance on all in-domain and OOD settings tested compared to existing methods. For six OOD tasks specifically, while previous methods exhibited an average performance decrease of approximately 4.6% after post training, ReGenesis delivers around 6.1% performance improvement. We also conduct in-depth analysis of our framework and show ReGenesis is effective across various LLMs and design choices.