Pith. sign in

REVIEW 30 cited by

Aligning Large Language Models with Human: A Survey

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.12966 v1 pith:3PC66H3M submitted 2023-07-24 cs.CL

Aligning Large Language Models with Human: A Survey

classification cs.CL
keywords humanllmsalignmenttraininglanguagemethodsmodelssurvey
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large Language Models (LLMs) trained on extensive textual corpora have emerged as leading solutions for a broad array of Natural Language Processing (NLP) tasks. Despite their notable performance, these models are prone to certain limitations such as misunderstanding human instructions, generating potentially biased content, or factually incorrect (hallucinated) information. Hence, aligning LLMs with human expectations has become an active area of interest within the research community. This survey presents a comprehensive overview of these alignment technologies, including the following aspects. (1) Data collection: the methods for effectively collecting high-quality instructions for LLM alignment, including the use of NLP benchmarks, human annotations, and leveraging strong LLMs. (2) Training methodologies: a detailed review of the prevailing training methods employed for LLM alignment. Our exploration encompasses Supervised Fine-tuning, both Online and Offline human preference training, along with parameter-efficient training mechanisms. (3) Model Evaluation: the methods for evaluating the effectiveness of these human-aligned LLMs, presenting a multifaceted approach towards their assessment. In conclusion, we collate and distill our findings, shedding light on several promising future research avenues in the field. This survey, therefore, serves as a valuable resource for anyone invested in understanding and advancing the alignment of LLMs to better suit human-oriented tasks and expectations. An associated GitHub link collecting the latest papers is available at https://github.com/GaryYufei/AlignLLMHumanSurvey.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 30 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems

    cs.IR 2026-06 unverdicted novelty 7.0

    Mult-DPO provides a tractable multinomial surrogate for set-wise preference optimization in DPO that upper bounds the Plackett-Luce based loss for LLM recommender systems.

  2. Beyond Averages: Evaluating LLMs on Human Survey Replication at the Distributional Level

    cs.CL 2026-06 unverdicted novelty 7.0

    LLMs match condition-level patterns in a noodle purchase survey but fail to replicate distributional structure, with no model beating a pooled human baseline for purchase quantities.

  3. P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization

    cs.CV 2026-06 unverdicted novelty 7.0

    P²-DPO generates on-policy preference pairs targeting focus-and-enhance perception and visual robustness, combined with a calibration loss, to reduce hallucinations in LVLMs more effectively than human-feedback baselines.

  4. Indirect reciprocity beyond pairwise interactions

    physics.soc-ph 2026-04 unverdicted novelty 7.0

    A multiplayer indirect reciprocity framework shows that group cooperation is stabilized by the 'all good, help; one bad, halt' rule, producing bistability and hysteresis unlike monostable pairwise models.

  5. Probably Correct Optimal Stable Matching under Two-Sided Uncertainty

    cs.LG 2026-07 accept novelty 6.0

    Elimination algorithms identify the optimal stable matching with high probability under two-sided uncertainty by exploiting partial preferences and pervasive stable matchings, yielding sample-complexity and regret bou...

  6. Multi-Objective Exploration and Preference Optimization via Mutual Information

    cs.CL 2026-07 conditional novelty 6.0

    Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.

  7. Collective cooperation without individual fidelity in LLM agents

    physics.soc-ph 2026-06 unverdicted novelty 6.0

    LLM agents reproduce macro-level cooperation decline and stabilization in networked Prisoner's Dilemma but underestimate individual heterogeneity and produce different conditional cooperation rules than humans.

  8. Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating

    cs.CL 2026-06 unverdicted novelty 6.0

    Sycophancy fine-tuning induces emergent misalignment in LLMs that Alignment Gating can reverse by learning to suppress unsafe representations with generalization from narrow to broad domains.

  9. Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution

    cs.CL 2026-05 unverdicted novelty 6.0

    SCA applies the Information Bottleneck principle via NIBS and GIBS methods to identify erroneous steps in black-box LLM reasoning and boosts self-correction success by up to 13.5%.

  10. Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution

    cs.CL 2026-05 unverdicted novelty 6.0

    SCA framework applies Information Bottleneck to assign step-level confidence in black-box LLM reasoning traces, flagging errors and boosting self-correction success by up to 13.5% on math and QA tasks.

  11. See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding

    cs.CV 2026-05 unverdicted novelty 6.0

    SWIM aligns cross-attention maps from object nouns to ground-truth masks during training on the new NL-Refer dataset to enable text-only fine-grained video object understanding in MLLMs.

  12. Response Time Enhances Alignment with Heterogeneous Preferences

    cs.LG 2026-05 unverdicted novelty 6.0

    Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.

  13. PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs

    cs.AI 2026-05 unverdicted novelty 6.0

    PERSA combines RLHF with selective parameter-efficient updates to top transformer layers, raising style alignment scores from 35% to 96% on code feedback benchmarks while holding correctness near 100%.

  14. Facial-Expression-Aware Prompting for Empathetic LLM Tutoring

    cs.HC 2026-03 unverdicted novelty 6.0

    Facial expression signals via prompt integration improve empathetic responsiveness in LLM-based tutoring systems.

  15. A Survey on Large Language Model based Autonomous Agents

    cs.AI 2023-08 accept novelty 6.0

    A survey of LLM-based autonomous agents that proposes a unified framework for their construction and reviews applications in social science, natural science, and engineering along with evaluation methods and future di...

  16. Editorial Alignment: A Participatory Approach to Engaging Editorial Expertise in LLM-mediated Knowledge Dissemination

    cs.HC 2026-06 unverdicted novelty 5.0

    The paper introduces 'editorial alignment' as a participatory design practice that treats editorial standards as design artifacts to guide LLM behavior in knowledge dissemination, shown through workshops at one Nordic...

  17. In-Context Reward Adaptation for Robust Preference Modeling

    cs.LG 2026-05 unverdicted novelty 5.0

    Transformer model with response-time auxiliary input adapts reward models to unseen human preference domains via in-context learning from demonstrations.

  18. Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)

    cs.CL 2026-04 unverdicted novelty 5.0

    SSAS improves LLM sentiment prediction consistency and data quality by up to 30% on three review datasets via syntactic and semantic context assessment summarization.

  19. Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning

    cs.CL 2026-04 accept novelty 5.0

    LLM post-training is unified as off-policy or on-policy interventions that expand support for useful behaviors, reshape policies within reachable states, or consolidate behavior across training stages.

  20. POPI: Personalizing LLMs via Optimized Natural Language Preference Inference

    cs.CL 2025-10 unverdicted novelty 5.0

    POPI distills user preferences into reusable natural-language summaries via a shared inference model and conditions a generator on them, trained jointly with RL to improve personalization quality while cutting context...

  21. Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents

    cs.HC 2025-10 conditional novelty 5.0

    A 3x3 between-subjects experiment finds that risk-contingent autonomy in LLM agents attenuates personalization's negative effects on privacy concerns and trust via increased perceived control.

  22. Knowledge-Driven Hallucination in Large Language Models: An Empirical Study on Process Modeling

    cs.AI 2025-09 unverdicted novelty 5.0

    LLMs override explicit source evidence with internal knowledge when modeling business processes, creating a measurable reliability risk in analytical tasks.

  23. Multi-Objective Exploration and Preference Optimization via Mutual Information

    cs.CL 2026-07 unverdicted novelty 4.0

    MI-EPO maximizes joint conditional mutual information among responses, feedback, and preference vectors, using probabilistic routing to improve alignment and controllability in multi-objective LLM optimization.

  24. BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards

    cs.AI 2026-06 unverdicted novelty 4.0

    BV-Blend blends prompt-local and semantic-cluster historical reward statistics via SEM-derived weights to stabilize critic-free RL advantage estimation.

  25. Large Language Model-Brained GUI Agents: A Survey

    cs.AI 2024-11 unverdicted novelty 4.0

    A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.

  26. Baichuan 2: Open Large-scale Language Models

    cs.CL 2023-09 unverdicted novelty 4.0

    Baichuan 2 presents 7B and 13B LLMs trained on 2.6T tokens that match or exceed similar open models on MMLU, CMMLU, GSM8K, HumanEval and excel in medicine and law.

  27. A Survey on Large Language Models for Code Generation

    cs.CL 2024-06 unverdicted novelty 3.0

    A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark...

  28. A Survey on the Memory Mechanism of Large Language Model based Agents

    cs.AI 2024-04 accept novelty 3.0

    A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.

  29. A Survey on Knowledge Distillation of Large Language Models

    cs.CL 2024-02 accept novelty 3.0

    A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.

  30. A Comprehensive Overview of Large Language Models

    cs.CL 2023-07 unverdicted novelty 2.0

    A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.