{"data":{"id":"2425af9c-d936-4e76-b013-a7481308d00a","title":"A Survey of Progress in LLM Alignment From the Perspective of Reward Design","summary":"This review surveys reward design for aligning large language models, organized around four questions: how rewards are specified mathematically, how they are built through rule-based, data-driven and hybrid workflows, how they interact with optimization paradigms, and how they are assessed through benchmarks. It proposes a taxonomy linking structural choices to practical trade-offs and highlights trends such as hybrid supervision and reinforcement-learning-free alignment.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"http://ieeexplore.ieee.org/document/11361384","publishedAt":"2026-01-23T13:17:50.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-01-23T13:17:50.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":null,"llmSpecific":true,"classifierConfidence":0.85,"researchCategory":"peer_reviewed","atlasIds":null}}