Elo-Disentangled Player-Style Embeddings for Human Chess via Rating-Conditioned Residual Move Model

• URL: http://arxiv.org/abs/2606.25176v1
• Date: Tue, 23 Jun 2026 21:06:24 GMT
• Title: Elo-Disentangled Player-Style Embeddings for Human Chess via Rating-Conditioned Residual Move Model
• Abstract summary: We study representation learning for individual human chess style.<n>A per-player embedding is learned from a player's move history.<n>We argue that a strong rating-conditioned base plus a compact, Elo-disentangled embedding is an economical, interpretable model of individual style.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study representation learning for individual human chess style: a per-player embedding learned from a player's move history such that inner products measure stylistic similarity, while being approximately disentangled from playing strength (Elo). Our key design is a residual formulation: a rating-conditioned base move model (Maia-3 policy logits plus Stockfish-derived features, scored over Maia-2-proposed candidates) captures what a typical player of a given strength would play, and a frozen copy of it anchors a learned move encoder and a per-player vector z, so that z explains only deviations from rating-typical play. The base model improves move prediction over the strong Maia-3 policy by 27-37% relative NLL across the rating spectrum, with the largest gains at the top (2800+); Stockfish's marginal value grows monotonically with Elo (negligible at 900-1200, +0.085 nats at 2800+). On a shared Elo-stratified benchmark of 22,620 held-out decisions, top-1 move-matching rises monotonically from Maia-2 to Maia-3 to the Stockfish-augmented base (0.51 -> 0.57 -> 0.68): the base is +33% relative top-1 over Maia-2 and +19% over Maia-3 (30% lower NLL), with the engine-feature lift largest at high Elo. The player embedding adds little to raw move-matching on top of this base -- its marginal top-1 gain falls within the 95% confidence interval -- and its value is instead representational: z generalizes to held-out decisions without overfitting, re-identifies players from disjoint games above chance, and a linear probe recovers rating from z with only R^2 = 0.06 (no better nonlinearly), evidence it captures style on an Elo-orthogonal axis. We argue that a strong rating-conditioned base plus a compact, Elo-disentangled embedding -- separating typical play from individual deviation -- is an economical, interpretable model of individual style, an alternative to per-player preference fine-tuning.

Related papers

• CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation [49.0564416580726]
  We distill the compositional judgments of a cross-attentive reranker into an embedding model.<n>We show that CORE-RERANKER-8B achieves an 82.7% total average, outperforming Jina-Reranker by 10.7 points.<n>The improvements transfer to the MCMR benchmark without sacrificing retrieval performance on COCO and Flickr30K.
  arXiv  Detail & Related papers  (2026-09-03T16:50:29Z)
• Whose Gold? Annotator-Pool Disagreement Is Large at the Item Level, and Hidden by Small Leaderboards [0.0]
  We show that preference benchmarks are built by hiring annotators, and the identity of those annotators is treated as an implementation detail.<n>On the 2,885 MultiPref items where both pools are internally unanimous, so no tie-breaking convention is consulted at all.<n>Yet on both corpora the resulting model leaderboards are bit-identical: Kendall tau = 1.00 with zero of six models displaced.
  arXiv  Detail & Related papers  (2026-08-17T00:19:52Z)
• ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess [0.08460698440162888]
  ChessMimic is a system of three encoder-only transformers for move, thinking-time, and outcome prediction.<n>On a held-out month-wide slice of Lichess Rated Blitz games ChessMimic's human move prediction accuracy outperforms Maia-2 in every Elo band.<n>A public demo is at 1e4.ai and we release code, per-band weights, and the C++ data-filter pipeline code in GitHub.
  arXiv  Detail & Related papers  (2026-06-03T05:42:39Z)
• Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers [3.692740024498697]
  A human-like chess engine should mimic the style, errors, and consistency of a strong human player rather than maximize playing strength.<n>We show that training from move sequences alone forces a model to learn two capabilities: state tracking, which reconstructs the board from move history, and decision quality, which selects good moves from that reconstructed state.<n>We formalize this tension as a dual-capability bottleneck, P = min(T,Q), where overall performance is limited by the weaker capability.
  arXiv  Detail & Related papers  (2026-03-31T14:01:39Z)
• Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation [17.451562591754698]
  We examine whether a draw genuinely means that the two models are equal.<n>We conjecture that draws are more indicative of query difficulty.<n>We recommend future rating systems to reconsider existing draw semantics.
  arXiv  Detail & Related papers  (2025-10-02T17:59:41Z)
• Multiplayer Nash Preference Optimization [79.15013211640566]
  Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models (LLMs) with human preferences.<n>Recent studies have reframed alignment as a two-player Nash game, giving rise to Nash learning from human feedback (NLHF)<n>We introduce Multiplayer Nash Preference Optimization (MNPO), a novel framework that generalizes NLHF to the multiplayer regime.
  arXiv  Detail & Related papers  (2025-09-27T04:18:33Z)
• CHARM: Calibrating Reward Models With Chatbot Arena Scores [31.599659350165354]
  Reward models (RMs) play a crucial role in Reinforcement Learning from Human Feedback by serving as proxies for human preferences in aligning large language models.<n>We identify a model preference bias in RMs, where they systematically assign disproportionately high scores to responses from certain policy models.<n>To address this issue, we propose a calibration method named CHatbot Arena Reward Modeling (CHARM) that leverages Elo scores from the Arena leaderboard to mitigate RM overvaluation.
  arXiv  Detail & Related papers  (2025-04-14T09:51:09Z)
• Chess Rating Estimation from Moves and Clock Times Using a CNN-LSTM [11.340099493701029]
  We propose a method to estimate player ratings directly from game moves and clock times. Our model architecture comprises a CNN to learn positional features, which are integrated with clock-time data into a Bidirectional LSTM. This model is the first to use no hand-crafted features to estimate chess ratings and also the first to output a rating prediction after each move.
  arXiv  Detail & Related papers  (2024-09-17T19:19:16Z)
• Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning [55.65738319966385]
  We propose a novel online algorithm, iterative Nash policy optimization (INPO)<n>Unlike previous methods, INPO bypasses the need for estimating the expected win rate for individual responses.<n>With an LLaMA-3-8B-based SFT model, INPO achieves a 42.6% length-controlled win rate on AlpacaEval 2.0 and a 37.8% win rate on Arena-Hard.
  arXiv  Detail & Related papers  (2024-06-30T08:00:34Z)
• WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild [57.272096543738336]
  We introduce WildBench, an automated evaluation framework designed to benchmark large language models (LLMs) WildBench consists of 1,024 tasks carefully selected from over one million human-chatbot conversation logs. We have developed two metrics, WB-Reward and WB-Score, which are computable using advanced LLMs.
  arXiv  Detail & Related papers  (2024-06-07T09:15:44Z)
• Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
  Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences. We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium.
  arXiv  Detail & Related papers  (2024-05-01T17:59:20Z)
• Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoning [67.33899440998175]
  Chain-of-Opinion (COO) is a simple four-step solution modeling which and how to reason with personae.<n>COO distinguishes between explicit personae (demographics and ideology) and implicit personae (historical opinions)<n>COO efficiently achieves new state-of-the-art opinion prediction via prompting with only 5 inference calls, improving prior techniques by up to 4%.
  arXiv  Detail & Related papers  (2023-11-14T18:48:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.