Pith. sign in

REVIEW 15 cited by

LiPO: Listwise Preference Optimization through Learning-to-Rank

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 2402.01878 v3 pith:POHXFJNM submitted 2024-02-02 cs.CL cs.LG

classification cs.CLcs.LG
keywords preferencefeedbacklistrankingresponsesalignmenthumanlistwise
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Aligning language models (LMs) with curated human feedback is critical to control their behaviors in real-world applications. Several recent policy optimization methods, such as DPO and SLiC, serve as promising alternatives to the traditional Reinforcement Learning from Human Feedback (RLHF) approach. In practice, human feedback often comes in a format of a ranked list over multiple responses to amortize the cost of reading prompt. Multiple responses can also be ranked by reward models or AI feedback. There lacks such a thorough study on directly fitting upon a list of responses. In this work, we formulate the LM alignment as a \textit{listwise} ranking problem and describe the LiPO framework, where the policy can potentially learn more effectively from a ranked list of plausible responses given the prompt. This view draws an explicit connection to Learning-to-Rank (LTR), where most existing preference optimization work can be mapped to existing ranking objectives. Following this connection, we provide an examination of ranking objectives that are not well studied for LM alignment with DPO and SLiC as special cases when list size is two. In particular, we highlight a specific method, LiPO-$\lambda$, which leverages a state-of-the-art \textit{listwise} ranking objective and weights each preference pair in a more advanced manner. We show that LiPO-$\lambda$ can outperform DPO variants and SLiC by a clear margin on several preference alignment tasks with both curated and real rankwise preference data.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 15 Pith papers

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

  1. MentalThink: Shaping Thoughts in Mental SVG World

    cs.AI 2026-07 conditional novelty 7.0 of 10

    MLLMs that generate and render SVG sketches as multi-turn intermediate reasoning steps reach 55.1% on VSIBench and 76.0% on MindCube, far above the Qwen2.5-VL-7B backbone.

  2. LPOI: Listwise Preference Optimization for Vision Language Models

    cs.CV 2025-05 conditional novelty 7.0 of 10

    LPOI reduces VLM hallucination by training the model to prefer the original image over progressively masked versions of the same image, using a listwise ranking loss built from pairwise preference data.

  3. Multi-Turn On-Policy Distillation with Prefix Replay

    cs.LG 2026-07 conditional novelty 6.0 of 10

    ReOPD offline-distills multi-turn agentic LLMs via teacher-prefix replay plus step-decay sampling, matching online OPD accuracy at ≥4× speed with zero tool calls.

  4. HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    HSCR uses visual token dropout and logit contrast to construct self-generated dispreferred answers, then trains a medical VLM with explicit and implicit preference losses, improving zero-shot Rad-VQA, SLAKE, and PathV...

  5. MPO: Multilingual Safety Alignment via Reward Gap Optimization

    cs.CL 2025-05 conditional novelty 6.0 of 10

    MPO reduces jailbreak success in multilingual LLMs by regressing target-language reward gaps onto the English reward gap, outperforming DPO and related methods while preserving utility.

  6. ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A reward-oriented influence scoring method that uses pairwise preference loss to select 5% of instruction-tuning data, outperforming similarity-based selection baselines on SHP, SE, and HH-RLHF.

  7. Reward Modeling with Ordinal Feedback: Wisdom of the Crowd

    cs.LG 2024-11 conditional novelty 6.0 of 10

    The paper generalizes Bradley-Terry reward modeling to ordinal feedback labels and proves that, under a marginal unbiasedness assumption, finer-grained labels reduce Rademacher complexity and can improve reward learning.

  8. A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

    cs.CR 2025-04 conditional novelty 5.0 of 10

    A large collaborative survey organizes LLM and LLM-agent safety issues into a full-stack lifecycle framework from data preparation to deployment.

  9. 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...

  10. PerPO: Perceptual Preference Optimization via Discriminative Rewarding

    cs.AI 2025-02 conditional novelty 5.0 of 10

    PerPO trains multimodal LLMs by ranking their candidate answers with deterministic visual rewards (IoU, edit distance) and using the reward differences as margins in listwise preference optimization.

  11. HAEPO: History-Aggregated Exploratory Policy Optimization

    cs.LG 2025-08 conditional novelty 4.0 of 10

    HAEPO weights each trajectory by its softmax-normalized cumulative log-likelihood, adds entropy and KL penalties, and matches or slightly surpasses PPO, GRPO, and DPO on small RL and summarization tasks.

  12. LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs

    cs.CV 2025-06 conditional novelty 4.0 of 10

    LeanPO improves Video-LLM alignment by using a reference-free average-likelihood reward, self-generated winning/losing pairs, and dynamic label smoothing, yielding gains on six video benchmarks.

  13. Advancing LLM Safe Alignment with Safety Representation Ranking

    cs.CL 2025-05 reject novelty 4.0 of 10

    Safety Representation Ranking (SRR) trains a lightweight transformer on internal LLM hidden states to rank candidate responses by safety, reporting high pairwise accuracy on safety benchmarks.

  14. Controllable Protein Sequence Generation with LLM Preference Optimization

    cs.AI 2025-01 conditional novelty 4.0 of 10

    CtrlProt uses multi-listwise preference optimization with Rosetta energy and structural embedding similarity to improve controllable protein sequence generation.

  15. Reward Models in Deep Reinforcement Learning: A Survey

    cs.LG 2025-06 conditional novelty 3.0 of 10

    A structured survey of reward modeling in deep RL, proposing a three-axis taxonomy and reviewing applications and evaluation methods.

Pith tools