Retrieval-augmented generation needs generation to follow retrieved evidence across shifting domains and prompt layouts, but training a new stronger model per task is costly.To this end, we propose GRAD, an adaptive decodingtime framework that keeps the base generator fixed and composes small, objective-specific guidance at inference.A key advantage of this design is enabling mix and match diverse RAG objectives: model scaling (MS), domain adaptation (DA) and positional debiasing (DB) can be integrated as token-level guidance terms, and new objectives can be easily plugged in.Across public benchmarks and private settings with no in-domain labels, GRAD improves accuracy with favorable latency, offering strong trade-offs versus scaling while reliably activating helpful objectives and suppressing harmful ones, adaptively to tasks.

Mitigating positional bias of language models (LMs) for listwise inputs is a well-known and important problem (e.g., lost-in-the-middle). While zero-shot order-invariant LMs have been proposed to solve this issue, their success on practical listwise problems has been limited. In this work, as a first contribution, we identify and overcome two limitations to make zero-shot invariant LMs more practical: (1) training and inference distribution mismatch arising from modifying positional ID assignments to enforce invariance, and (2) failure to adapt to mixture of order-invariant and sensitive inputs in practical listwise problems. Then, to overcome these issues we propose (1) RoToR, a zero-shot invariant LM for genuinely order-invariant inputs with minimal modifications of positional IDs, and (2) Selective Routing, an adaptive framework that handles both order-invariant and order-sensitive inputs in listwise tasks. On the Lost in the middle (LitM), Knowledge Graph QA (KGQA), and MMLU benchmarks, we show that RoToR with Selective Routing can effectively handle practical listwise input tasks in a zero-shot manner (https://github.com/soyoung97/RoToR)

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.

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. 1 Index Generated Requirements Generated Code (manually validated) (validated by Ground Truth Test Cases) HumanEval-NFR/51 0 Correct Passed 1 Correct Passed 2 Correct Passed 3 Correct

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 reward shaping method 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.1

Despite the success of neural machine translation models, tensions between fluency of optimizing target language modeling and sourcefaithfulness 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.

This paper studies Code-Text Representation (CTR) learning, aiming to learn general-purpose representations that support downstream code/text applications such as code search, finding code matching textual queries. However, state-of-the-arts do not focus on matching the gap between code/text modalities. In this paper, we complement this gap by providing an intermediate representation, and view it as “explanation.” Our contribution is three fold: First, we propose four types of explanation utilization methods for CTR, and compare their effectiveness. Second, we show that using explanation as the model input is desirable. Third, we confirm that even automatically generated explanation can lead to a drastic performance gain. To the best of our knowledge, this is the first work to define and categorize code explanation, for enhancing code understanding/representation.