Towards Explainable Adjudicative Variance: Quantifying Judicial Discretion via Gated Multi-Task Learning

• URL: http://arxiv.org/abs/2606.27069v2
• Date: Fri, 26 Jun 2026 07:36:53 GMT
• Title: Towards Explainable Adjudicative Variance: Quantifying Judicial Discretion via Gated Multi-Task Learning
• Abstract summary: Legal outcome prediction must disentangle objective case facts from adjudicative context.<n>We propose a Judge-Aware Gated Multi-Task Learning architecture that explicitly models this distinction.<n>We evaluate our approach on 13,937 UK Employment Tribunal decisions.
• Score: 9.159064044398315
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Legal outcome prediction must disentangle objective case facts from adjudicative context. Merit-based rulings rely on factual evidence while technical disposals may hinge on judicial discretion. We propose a Judge-Aware Gated Multi-Task Learning architecture that explicitly models this distinction. We introduce a fine-grained outcome taxonomy to supervise the encoder, enforcing a structural regularization that disentangles distinct semantic pathways. This granular legal curriculum enables our Gated Fusion mechanism to dynamically modulate reliance on judge identity. We evaluate our approach on 13,937 UK Employment Tribunal decisions. We benchmark our design against supervised fine-tuning (SFT) of a Gemma-4 26B-A4B backbone, in which judge identity and the taxonomy are injected as prompt tokens or autoregressive output targets. The two contextual signals compose only weakly when forced through a single autoregressive channel. In contrast, coupling a LoRA-adapted Gemma-4 encoder with our gated architecture defines a new state of the art on this benchmark while requiring an order of magnitude fewer trainable parameters than the generative SFT baselines, with gains concentrated on the most ambiguous and rarest outcome classes. Beyond accuracy, the architecture is interpretable; learned judge embeddings and calibration profiles localize the cases where adjudicative context drives the prediction. These results indicate that, for identity-conditioned classification of legal outcomes, the choice of conditioning interface dominates scale: differentiable structured composition yields more accurate, more parameter-efficient models than prompt-based composition over a substantially larger backbone.

Related papers

• C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning [0.6138671548064355]
  Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning.<n>We introduce C2-Faith, a benchmark that targets two complementary dimensions of faithfulness: causality (does each step logically follow from prior context?) and coverage.<n>We evaluate three frontier judges under three tasks: binary causal detection, causal step localization, and coverage scoring.
  arXiv  Detail & Related papers  (2026-03-05T13:36:47Z)
• CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignment [15.634714514096487]
  Vision-language models like CLIP suffer from systematic misclassifications among visually and semantically similar categories.<n>We propose CAPT, a Confusion-Aware Prompt Tuning framework that enables models to learn from their own misalignment.
  arXiv  Detail & Related papers  (2026-03-03T03:20:23Z)
• The Judge Who Never Admits: Hidden Shortcuts in LLM-based Evaluation [17.386684382460242]
  Large language models (LLMs) are increasingly used to evaluate system outputs in tasks such as reasoning, question answering, and creative writing.<n>We test this ideal via controlled cue perturbations-synthetic metadata labels injected into evaluation prompts for six judge models.<n>We study six cue families: source, temporal, age, gender, ethnicity, and educational status.
  arXiv  Detail & Related papers  (2026-02-08T14:45:23Z)
• JAF: Judge Agent Forest [8.150475950851359]
  We introduce JAF: Judge Agent Forest, a framework in which the judge agent conducts joint inference across a cohort of query--response pairs.<n>We develop a flexible locality-sensitive hashing algorithm that learns informative binary codes by integrating semantic embeddings.<n>We validate JAF with an empirical study on the demanding task of cloud misconfigs triage in large-scale cloud environments.
  arXiv  Detail & Related papers  (2026-01-29T19:42:42Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• When in Doubt, Deliberate: Confidence-Based Routing to Expert Debate for Sexism Detection [7.299050989302629]
  We propose a framework to address the combined effects of (i) underrepresentation, (ii) noise, and (iii) conceptual ambiguity in both data and model predictions.<n>Our approach achieves state-of-the-art results across several benchmarks, with a +2.72% improvement in F1 on Tasks EXIST 2025 Task 1.1, and a gains of +4.48% and +1.30% on EDOS A and B, respectively.
  arXiv  Detail & Related papers  (2025-12-21T05:48:57Z)
• SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking [58.475471437150674]
  We propose sequential watermarking for soft prompts (SWAP)<n>SWAP encodes watermarks through a specific order of defender-specified out-of-distribution classes.<n>Experiments on 11 datasets demonstrate SWAP's effectiveness, harmlessness, and robustness against potential adaptive attacks.
  arXiv  Detail & Related papers  (2025-11-05T13:48:48Z)
• An Ontology-Driven Graph RAG for Legal Norms: A Structural, Temporal, and Deterministic Approach [0.0]
  RAG systems in the legal domain face a critical challenge: standard, flat-text retrieval is blind to the hierarchical, diachronic, and causal structure of law, leading to anachronistic and unreliable answers.<n>This paper introduces the Structure-Aware Temporal Graph RAG (SAT-Graph RAG), an ontology-driven framework designed to overcome these limitations by explicitly modeling the formal structure and diachronic nature of legal norms.
  arXiv  Detail & Related papers  (2025-04-29T18:36:57Z)
• DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment [55.91429725404988]
  We introduce DELTA, a discriminative model designed for legal case retrieval. We leverage shallow decoders to create information bottlenecks, aiming to enhance the representation ability. Our approach can outperform existing state-of-the-art methods in legal case retrieval.
  arXiv  Detail & Related papers  (2024-03-27T10:40:14Z)
• When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
  Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
  arXiv  Detail & Related papers  (2023-07-06T04:13:57Z)
• SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval [75.05173891207214]
  Legal case retrieval plays a core role in the intelligent legal system. Most existing language models have difficulty understanding the long-distance dependencies between different structures. We propose a new Structure-Aware pre-traIned language model for LEgal case Retrieval.
  arXiv  Detail & Related papers  (2023-04-22T10:47:01Z)
• Relational Proxies: Emergent Relationships as Fine-Grained Discriminators [52.17542855760418]
  We propose a novel approach that leverages information between the global and local part of an object for encoding its label. We design Proxies based on our theoretical findings and evaluate it on seven challenging fine-grained benchmark datasets. We also experimentally validate our theory and obtain consistent results across multiple benchmarks.
  arXiv  Detail & Related papers  (2022-10-05T11:08:04Z)

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.