Code generation with large language models has shown significant promise, especially when employing retrieval-augmented generation (RAG) with few-shot examples. However, selecting effective examples that enhance generation quality remains a challenging task, particularly when the target programming language (PL) is underrepresented. In this study, we present two key findings: (1) retrieving examples whose presented algorithmic plans can be referenced for generating the desired behavior significantly improves generation accuracy, and (2) converting code into pseudocode effectively captures such algorithmic plans, enhancing retrieval quality even when the source and the target PLs are different. Based on these findings, we propose Plan-as-query Example Retrieval for few-shot prompting in Code generation (PERC), a novel framework that utilizes algorithmic plans to identify and retrieve effective examples. We validate the effectiveness of PERC through extensive experiments on the CodeContests, HumanEval and MultiPL-E benchmarks: PERC consistently outperforms the state-of-the-art RAG methods in code generation, both when the source and target programming languages match or differ, highlighting its adaptability and robustness in diverse coding environments.

Retrieval-augmented generation (RAG) has emerged as a popular approach to steering the output of a large language model (LLM) by incorporating retrieved contexts as inputs. However, existing work observed the generator bias, such that improving the retrieval results may negatively affect the outcome. In this work, we show such bias can be mitigated, from inference scaling, aggregating inference calls from the permuted order of retrieved contexts. The proposed Mixture-of-Intervention (MoI) explicitly models the debiased utility of each passage with multiple forward passes to construct a new ranking. We also show that MoI can leverage the retriever’s prior knowledge to reduce the computational cost by minimizing the number of permutations considered and lowering the cost per LLM call. We showcase the effectiveness of MoI on diverse RAG tasks, improving ROUGE-L on MS MARCO and EM on HotpotQA benchmarks by ~7 points.

With the adoption of retrieval-augmented generation (RAG), large language models (LLMs) are expected to ground their generation to the retrieved contexts. Yet, this is hindered by position bias of LLMs, failing to evenly attend to all contexts. Previous work has addressed this by synthesizing contexts with perturbed positions of gold segment, creating a position-diversified train set. We extend this intuition to propose consistency regularization with augmentation and distillation. First, we augment each training instance with its position perturbation to encourage consistent predictions, regardless of ordering. We also distill behaviors of this pair, although it can be counterproductive in certain RAG scenarios where the given order from the retriever is crucial for generation quality. We thus propose CORD, balancing COnsistency and Rank Distillation: CORD adaptively samples noise-controlled perturbations from an interpolation space, ensuring both consistency and respect for the rank prior. Empirical results show this balance enables CORD to outperform consistently in diverse RAG benchmarks.

This paper addresses the challenge of detecting query variants—pairs of queries with identical intents. One application in commercial search engines is reformulating user queries with its variant online. While measuring pairwise query similarity has been an established standard, it often falls short of capturing semantic equivalence when word forms or order differ. We propose leveraging the retrieval as an environment feedback (EF), based on the premise that desirable retrieval outcomes from equivalent queries should be interchangeable. Experimental results on both proprietary and public datasets demonstrate the efficacy of the proposed method, both with and without LLM calls.

This paper aims to extend the code generation capability of large language models (LLMs) to automatically manage comprehensive software requirements from given textual descriptions. Such requirements include both functional (i.e. achieving expected behavior for inputs) and non-functional (e.g., time/space performance, robustness, maintainability) requirements. However, textual descriptions can either express requirements verbosely or may even omit some of them. We introduce ARCHCODE, a novel framework that leverages in-context learning to organize requirements observed in descriptions and to extrapolate unexpressed requirements from them. ARCHCODE generates requirements from given descriptions, conditioning them to produce code snippets and test cases. Each test case is tailored to one of the requirements, allowing for the ranking of code snippets based on the compliance of their execution results with the requirements. Public benchmarks show that ARCHCODE enhances to satisfy functional requirements, significantly improving Pass@k scores.Furthermore, we introduce HumanEval-NFR, the first evaluation of LLMs’ non-functional requirements in code generation, demonstrating ARCHCODE’s superiority over baseline methods. The implementation of ARCHCODE and the HumanEval-NFR benchmark are both publicly accessible.

This paper studies the use of reinforcement learning for conditional text generation, which overcomes the limitation of the prevalent supervised maximum likelihood estimation approach. However, it still suffers from challenges including the large action space and the delayed reward, as the reward can be computed only after an entire sequence is generated. To address these challenges, we propose a method that provides partial rewards for intermediate actions taken on partial sequences. This enables the model to promptly prioritize actions that lead to the generation of more desirable sequences. Our method’s key contribution lies in its focus on distinguishing relatively more desirable actions rather than striving to precisely estimate pointwise values for arbitrary partial sequences. Instead, our model learns to discern the relative desirability between pairs of actions, or rank actions in a pairwise manner, only when necessary and feasible. This is materialized in an efficient way by leveraging the prefix tree constructed from the sampled sequences. Experimental results on paraphrase generation and constrained machine translation tasks showcase the effectiveness of our method.

Large language models often struggle to predict runtime behavior in code generation tasks, leading to a reliance on rejection sampling (best-of-n) to generate multiple code snippets then select the best. Our distinction is reducing sampling costs, without compromising generation quality. We introduce EFFICODE, a novel framework that prioritizes sampling on test problems that models can solve. We show how EFFICODE estimates solvability to optimize computational costs during multiple sampling. Based on empirical evidence, EFFICODE consistently demonstrates reduced sampling budgets while maintaining comparable code generation performance, especially when problems are challenging. In addition, utilizing EFFICODE to rank sampled code snippets also shows its effectiveness in answer code selection for reducing temporal costs, by not requiring any execution or test case generation.

Despite the success of neural machine translation models, tensions between fluency of optimizing target language modeling and source-faithfulness remain as challenges. Previously, Conditional Bilingual Mutual Information (CBMI), a scoring metric for the importance of target sentences and tokens, was proposed to encourage fluent and faithful translations. The score is obtained by combining the probability from the translation model and the target language model, which is then used to assign different weights to losses from sentences and tokens. Meanwhile, we argue this metric is not properly normalized, for which we propose Normalized Pointwise Mutual Information (NPMI). NPMI utilizes an additional language model on source language to approximate the joint likelihood of source-target pair and the likelihood of the source, which is then used for normalizing the score. We showed that NPMI better captures the dependence between source-target and that NPMI-based token-level adaptive training brings improvements over baselines with empirical results from En-De, De-En, and En-Ro translation tasks.