Pith. sign in

REVIEW 31 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

classification cs.CL
keywords humanllmsalignmenttraininglanguagemethodsmodelssurvey
verification ladder T0 review T1 audit T2 compute T3 formal
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). Continue with ORCID to comment.

Forward citations

Cited by 31 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 54 citations worldwide. Full citation record

  1. CrossPipe: Towards Optimal Pipeline Schedules for Cross-Datacenter Training

    cs.DC 2025-06 conditional novelty 7.0 of 10

    CrossPipe generates latency- and bandwidth-aware pipeline schedules that cut emulated cross-datacenter LLM training time by up to 33.6%.

  2. Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL

    cs.AI 2026-07 conditional novelty 6.0 of 10

    PRISM trains one positive policy per reward plus one global negative policy and merges their token logits, improving multi-reward RL for LLMs with inference-time controllability.

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

    cs.LG 2026-07 accept novelty 6.0 of 10

    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...

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

    cs.HC 2026-03 unverdicted novelty 6.0 of 10

    Feeding LLM tutors a text description or AUM-selected frame of a student's facial expression improves rated empathetic responsiveness across three backbones.

  5. GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

    cs.LG 2026-02 conditional novelty 6.0 of 10

    Action-weighted SFT plus KL-regularized GRPO on a curated 81K reasoning dataset lifts open-source GUI agents by 11–22 points on online task-completion benchmarks.

  6. SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences

    cs.LG 2025-09 reject novelty 6.0 of 10

    SharedRep-RLHF learns a shared preference representation across groups to improve worst-case reward estimates for minority annotators, but the theoretical guarantees are undermined by proof errors.

  7. Exploring the Impact of Instruction-Tuning on LLM's Susceptibility to Misinformation

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Instruction tuning shifts LLM susceptibility to misinformation from assistant-provided text to user-provided text, making user-role misinformation more likely to override the model's correct parametric knowledge.

  8. Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation

    cs.AI 2025-06 reject novelty 6.0 of 10

    LLM-based long-horizon event simulation, used as a reward signal, is claimed to improve safety alignment and indirect-harm detection, but evaluation confounds simulation with the capability of the external projector model.

  9. Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework

    cs.HC 2025-06 conditional novelty 6.0 of 10

    Structured moral prompts, especially first-principles reasoning, improve LLM moral classification accuracy across 12 open models and four benchmarks, and reasoning distillation transfers these gains to a 3B model.

  10. From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment

    cs.CL 2025-06 conditional novelty 6.0 of 10

    SP-PRM trains process reward models from outcome reward models via score and preference consistency, improving reward-guided search on dialogue, summarization, and reasoning tasks.

  11. Tag-Evol: Achieving Efficient Instruction Evolving via Tag Injection

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Tag-Evol generates harder, more diverse instruction data by injecting sampled knowledge tags into seed instructions, improving downstream SFT accuracy across math, code, and general benchmarks.

  12. Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models

    cs.AI 2025-02 conditional novelty 6.0 of 10

    Forcing a self-rewarding LLM's generative judge and implicit DPO reward to agree on preference labels substantially improves its AlpacaEval 2.0 alignment score.

  13. JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation

    cs.CR 2025-02 conditional novelty 6.0 of 10

    JBShield detects jailbreaks by checking whether a prompt activates both a toxic concept and a jailbreak concept inside an LLM, then steers those concepts to produce a safe refusal.

  14. SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling

    cs.LG 2026-06 conditional novelty 5.0 of 10

    A LoRA update split into several fixed, differently-scaled low-rank experts with orthogonal input directions improves fine-tuning accuracy at the same parameter count.

  15. Toward Preference-aligned Large Language Models via Residual-based Model Steering

    cs.CL 2025-09 conditional novelty 5.0 of 10

    Preference signals in LLM residual streams can be distilled into inference-time steering vectors that improve math and code benchmarks using only 100 preference pairs.

  16. Path to Intelligence: Measuring Similarity between Human Brain and Large Language Model Beyond Language Task

    q-bio.NC 2025-08 conditional novelty 5.0 of 10

    LLM hidden states can be linearly projected onto human intracranial EEG recorded during a text-translated sensory-motor anticipation task, with moderate CKA alignment and similar response-time distributions.

  17. An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models

    cs.AI 2025-07 conditional novelty 5.0 of 10

    A training pipeline that scores a model's own responses for semantic, factual, and safety uncertainty, builds preference pairs from those scores, and trains in three difficulty stages improves reported alignment score...

  18. Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models

    cs.CL 2025-05 reject novelty 5.0 of 10

    MARA aligns LLMs with human preferences by training a 4M-parameter MLP to accept or reject candidate tokens, avoiding full-model fine-tuning, with measured gains based on the same reward models used in training.

  19. One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs

    cs.CR 2025-05 conditional novelty 5.0 of 10

    ArrAttack fine-tunes a judge on the SmoothLLM defense, uses it to filter rewriting-attack data, and trains a generator that produces jailbreak prompts transferring across defenses.

  20. Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Preference signals in LLM alignment are concentrated in early response tokens, so models trained on data truncated to the first half perform as well as or better than those trained on full responses.

  21. Data2Concept2Text: An Explainable Multilingual Framework for Data Analysis Narration

    cs.LO 2025-02 conditional novelty 5.0 of 10

    A six-stage Prolog/CLP tree-rewriting pipeline converts concept trees into multilingual natural language sentences with explicit rule traces, demonstrated on data narration and an ICLP call-for-papers example.

  22. Salamandra Technical Report

    cs.CL 2025-02 conditional novelty 5.0 of 10

    Salamandra is an open, from-scratch multilingual LLM family with 2B, 7B, and 40B checkpoints, instruction-tuned variants, a vision proof-of-concept, and detailed evaluations across Iberian and European languages.

  23. LLM Alignment as Retriever Optimization: An Information Retrieval Perspective

    cs.CL 2025-02 conditional novelty 5.0 of 10

    LARPO, an iterative preference optimization method that adapts information retrieval techniques such as listwise ranking losses, hard negatives, and candidate lists, is claimed to substantially improve LLM alignment o...

  24. FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain

    cs.CL 2025-09 conditional novelty 4.0 of 10

    Unanimous voting between NLI and chain-of-thought fact-checking yields scores closest to medical expert judgments on three of four tasks in the new FActBench benchmark.

  25. A Comprehensive Evaluation framework of Alignment Techniques for LLMs

    cs.CL 2025-08 unverdicted novelty 4.0 of 10

    The paper proposes a multi-dimensional framework to evaluate and compare LLM alignment techniques.

  26. The Fair Game: Auditing & Debiasing AI Algorithms Over Time

    cs.AI 2025-08 unverdicted novelty 4.0 of 10

    Proposes 'Fair Game', a reinforcement-learning loop in which an auditor's bias criteria, updatable over time, steer a debiasing agent that adapts an ML model's predictions.

  27. Reliable Annotations with Less Effort: Evaluating LLM-Human Collaboration in Search Clarifications

    cs.IR 2025-07 reject novelty 4.0 of 10

    LLMs alone annotate search clarifications unreliably; adding confidence-based selective human review cuts effort 24-45% in simulation, but the evaluation is partly built from the ground truth it predicts.

  28. Crowd-SFT: Crowdsourcing for LLM Alignment

    cs.HC 2025-06 conditional novelty 4.0 of 10

    A competitive multi-group fine-tuning framework with point rewards correlated to Shapley values reduced simulated model distance by up to 55% and tracked user contributions reasonably in vector-space experiments.

  29. Large Language Models for EEG: A Comprehensive Survey and Taxonomy

    eess.SP 2025-06 conditional novelty 4.0 of 10

    A taxonomy and review of studies applying large language models to EEG signals, organized into four domains and three adaptation strategies.

  30. The Science of Evaluating Foundation Models

    cs.CL 2025-02 conditional novelty 3.0 of 10

    A survey-and-checklist proposal that organizes LLM evaluation into an ABCD framework (Algorithm, Big Data, Computation, Domain Expertise) for context-aware, documented assessment.

  31. Linguistics and Human Brain: A Perspective of Computational Neuroscience

    q-bio.NC 2026-02 unverdicted novelty 2.0 of 10

    A narrative review arguing that computational neuroscience, powered by LLM-based model–brain alignment, serves as the bridge between linguistic theory and neural data.

Pith tools