In-Domain Accuracy

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 23

Sep 29, 2026cs.AI

MLToolBench: Learning Tool-Augmented Agents for Machine Learning Development

Machine learning engineering (MLE) agents have made substantial progress, but learning through ML experimentation remains costly in time and computation. Synthetic environments reduce these costs while introducing variations in data and experimental settings that require task-specific diagnosis. Access to diagnostic tools alone does not ensure that agents learn when to use them or how to act on their findings. We introduce ToolMLBench, a suite of executable tools for data inspection, code verification, and experiment diagnosis, together with an SFT and RL pipeline for learning their use. Diagnostic calls acquire evidence whose value depends on subsequent decisions, so final outcomes provide limited guidance on which calls to reinforce. We address this challenge with SPICE, which measures how privileged context changes the likelihood of a sampled tool action and uses this difference as a turn-level reward alongside the final outcome. We train on 80 synthetic tasks and evaluate on 25 in-domain and 10 out-of-domain tasks. Providing tool interfaces and descriptions alone yields inconsistent gains across unadapted models. With the same diagnostic interface, our training pipeline raises in-domain success from 24.8% to 52.4% for Qwen3-8B and from 35.6% to 69.2% for Qwen3.5-35B-A3B. The latter also improves from 31% to 48% out-of-domain, supporting learned diagnostic tool use on held-out sources and targets.

Xin Yu, Lizhu Zhang, Jiamu Bai +7

Synthetic Task Diagnosis In-Domain Accuracy

Sep 29, 2026cs.RO

Losing the name before the box: measuring and repairing what narrow fine-tuning costs a detector outside its deployment vocabulary

A detector pretrained on a broad corpus is fine-tuned on a narrow domain, its in-domain accuracy improves, and it ships. We ask what happens meanwhile to its coverage of objects the vocabulary never names, which in obstacle detection and inspection carry the risk. No in-domain test set holds an example of one. We give a longitudinal protocol: one pretrained checkpoint against its own fine-tuned descendants. It tracks held-out top-

K

proposal coverage

C_τ

: of categories pretraining covered and the vocabulary omits, the share of boxes a detector's top

K

regions still cover. The quantity is the open-world proposal literature's; the longitudinal reading is not.

C_τ

falls while in-domain accuracy rises, on four architectures and three domains, by

5.12

to

63.35

points on boxes above

1024

px

^2

. No in-domain number identifies the fall, and neither does detection average precision, which charges a missed and a misnamed box alike. On the one architecture scoring both, adaptation costs

87\%

of the AP against a fifth of the coverage, and the naming goes first at all six depths of its freeze ladder, every run. What breaks is structured: three architectures sharing no pretraining run agree on which categories lose coverage, and those a model never learned do not lose any. A repair follows and needs no training: mixing a quarter of the pretrained state back, normalisation statistics included, raises coverage on every cell swept for at most

2.47

points of in-domain accuracy. Seeing it costs one extra evaluation pass.

Trung Minh Bui, Jongsul Moon, YoungOuk Kim +2

Intelligent Robotics Research Center, Korea Electronics Technology Institute, Seongnam, 13449, Republic of Korea.

Detection Performance In-Domain Accuracy Continual Fine-Tuning Top-K Longitudinal Obstacle Avoidance

Sep 12, 2026cs.RO

What Makes an Efficient VLA? Navigating Action-Head Design, Scaling, and Latency

Vision-Language-Action (VLA) models combine a pretrained vision encoder, a language backbone, and an action head, but their relative contribution has not been established under controlled, latency-paired conditions. We fix the backbone families (SigLIP2 and Qwen2.5) and the training pipeline, sweep action-head design and module scale, and pair each configuration with measured on-device latency. The study yields three findings. First, action-head performance is governed primarily by initialization rather than decoder architecture, loss, or inference budget: copying the last transformer layers of the language backbone into the head is the single largest lever, at no latency cost, and the only axis that helps at every module scale. Alignment also explains the other axes: flow matching and a heavier decoder pay off only while the head is misaligned and reverse once it is aligned, and extra inference passes give no measurable benefit; expressiveness appears to substitute for missing alignment. We read this as representation transfer: the aligned head keeps attending to the instruction's object nouns and stays close to the backbone in weight space rather than relearning to act from scratch. Because we reach alignment only through initialization, we offer this as the account that best organizes the measurements, not a demonstrated cause, and name the control that would settle it. Second, capacity pays only after alignment: the aligned action head is the highest-return module to scale. Third, those returns diminish sharply near the size today's

π

-series VLAs already use, so further growth buys little in-domain accuracy for its latency. These specify EffVLA, a compact model matching the strongest open-source VLAs on standard LIBERO, leading on most LIBERO-Plus perturbation axes at lower latency, and transferring to a real SO-ARM101 arm with the recipe unchanged.

Luoyang Sun, Guoyang Xia, Fengfa Li +9

Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences · AI Lab, The Yangtze River Delta +4

Vision Encoders Scaling In-Domain Accuracy

Sep 9, 2026cs.LG

Nonmaximal sums of maximally monotone operators under Rockafellar's constraint qualification

We construct counterexamples to Rockafellar's sum conjecture in which two maximally monotone operators satisfy the interior-domain condition but their sum is not maximally monotone, thereby providing the complete disproof of the conjecture. We establish a general construction theorem that computes the entire monotone polar of a class of graphs, gives a necessary and sufficient condition for their maximal monotonicity, and shows how a positive rank-one perturbation yields a nonmaximal sum under this condition. We verify the theorem's hypotheses and its maximality criterion on

c_0

, thereby obtaining a counterexample to the conjecture. Furthermore, we construct a bounded linear surjection from

\ell^1

onto

c_0

and use it to obtain the counterexample on

\ell^1

. Lean formalizations of the

c_0

counterexample and the pullback lemma are also provided.

Weifeng Yang

Monotone Variational Inequalities Monotonicity Maximization Counterexample Open Problems Structural Constraints+1

Sep 1, 2026cs.CV

A Benchmark for Vehicle Attribute Classification in Cross-Domain Surveillance Scenarios

Vehicle attribute analysis is a key component of Intelligent Transportation Systems (ITS), supporting applications such as vehicle identification, traffic monitoring, and forensic investigation. However, models trained under controlled conditions often degrade in real surveillance scenarios due to changes in viewpoint, occlusion, illumination, and sensor characteristics. This paper introduces Unconstrained Vehicle Identification Benchmark (UVIB), a benchmark for evaluating three operational vehicle-analysis tasks: front/rear orientation, occlusion-related suitability for Vehicle Make and Model Recognition (VMMR), and color clarity. The benchmark contains 84,835 vehicle images from seven public Brazilian datasets, grouped into surveillance and general acquisition domains, with unified binary annotations that were not jointly available in the original sources. Four representative architectures, EfficientNetV2-S, ResNet-50, ViT/B-16, and YOLO11s-cls, are evaluated under mixed-domain, cross-domain, and cross-dataset protocols. The results show that domain shift has a stronger impact than architecture choice, with substantial degradation in cross-domain settings, especially for VMMR suitability and color clarity. While orientation generalizes more reliably, VMMR suitability remains affected by class imbalance and ambiguous occlusions, and color clarity is highly sensitive to illumination and sensor modality. These findings highlight the need for benchmarks and evaluation protocols that explicitly measure operational robustness beyond standard in-domain accuracy. The proposed benchmark is publicly available at https://github.com/UFPR-IPASP-PR/uvib-vehicle-attributes/.

Sergio M. Silva, Otavio T. Remer, Gabriel E. Lima +3

Department of Informatics, Federal University of Paraná, Curitiba, Brazil · Graduate Program in Informatics, Pontifical Catholic University of Paraná, Curitiba, Brazil

Automotive Detection Video Surveillance In-Domain Accuracy

Aug 9, 2026cs.AI

MathShikkha: A Controlled Study of Answer-Only and Chain-of-Thought Supervision for Bangla Mathematical Reasoning in Small Language Models

Mathematical reasoning remains challenging in low-resource languages such as Bangla. We study whether teacher-generated Bangla Chain-of-Thought (CoT) supervision provides benefits beyond ordinary supervised fine-tuning. We construct \textsc{MathShikkha}, a Bangla mathematical reasoning dataset with GPT-5.4-generated rationales, and fine-tune four 4B--7B student models under a matched protocol in which answer-only and CoT conditions share data splits, response-only loss masking, decoding, and scoring, differing only in the training target. In-domain, CoT provides no significant improvement over answer-only fine-tuning for three stronger backbones (paired bootstrap 95% CIs include zero; exact McNemar

p \geq 0.17

), despite generating 15--52

\times

more tokens, but significantly improves the weaker 4B model by 18.56 points (

p < 0.0001

). On the larger, contamination-audited BanglaMATH benchmark, this pattern reverses: CoT significantly outperforms answer-only supervision for all four models by 20.1--28.1 points (all

p < 0.0001

). Answer-only fine-tuning also reduces out-of-domain accuracy below the base model for three models, whereas CoT preserves or improves it for all four. A human study with two co-author annotators, external-expert adjudication, and Cohen's

κ= 0.76

--

1.00

finds no significant CoT improvement over the base model on reasoning-content criteria; instead, its measurable effect is target-language adherence and producing inspectable reasoning. Overall, rationale supervision's value depends on backbone capability and distribution shift: in this setting, its main benefits are Bangla adherence, auditable reasoning, and out-of-domain robustness rather than improved in-domain reasoning validity.

Rahma Simin Ali, Jawad Hossain

Independent Researcher · University at Albany

Bangla Process-Level Supervision In-Domain Accuracy Language Pairs Puzzle

Aug 5, 2026cs.SE

The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Proposals

Frontier coding models now match or exceed strong human reference points on programming benchmarks, yet benchmark success does not imply maintainable software. Prompt-driven "vibe coding" is additive: new branches, guards, and fallbacks accumulate faster than obsolete logic is removed. We study the inverse problem-how an Al system should remove code when execution-verification capacity is finite. We formulate redundant-code reduction as proposal scheduling: a ranker orders single-statement deletion candidates, an execution suite accepts the first candidate that passes, and a budget bounds how many candidates may be tested. Our central observation is that candidate order, not model confidence, is the control surface a deployment can reason about. DELSCOUT instantiates two schedules. Given representative target-domain validation, a five-slot budget spends three slots on deterministic shortest-first candidates and two on complementary learned candidates; across nine MBPP replications with 0.5B, 0.6B, and 8B rankers this raises verified-deletion coverage by 9.5% relative (+6.7 accepted tasks) while consuming slightly fewer verifier calls than the matched static baseline. Without such validation the same rankers can lose coverage under shift, so we instead evaluate the complete static prefix first and append learned candidates only afterwards; for a deterministic verifier this makes coverage and character reduction non-decreasing by construction, at a measured 4.8-62.5% increase in verifier calls. MBPP+ then erases the in-domain advantage, showing that scheduling governs search while the test suite alone governs what "preserving behavior" means. The result is an auditable division of labor: models widen the search for removable code, order bounds the damage a mis-ranked proposal can do, and execution retains authority over every committed deletion.

Ruitong Li, Binjie Guo, Aisheng Mo +4

University of Hong Kong · Zhejiang University · Dalian University of Technology +1

Code Quality Verification Framework Deletion Provable Guarantees Redundancy Frontier Models+2

Jul 29, 2026cs.CV

Level, Sharpness, and Corpus: Why Zero-Shot OOD Detector Rankings Do Not Transfer

Selecting a zero-shot out-of-distribution (OOD) detector for a new deployment is typically based on benchmark rankings, implicitly assuming that the highest-ranked detector will transfer across domains. We show that this assumption does not hold. Through a controlled portability audit across seventeen in-distribution datasets, three vision-language models, and seven representative zero-shot OOD detectors, we find that detector rankings reverse across deployments, every detector exceeds

80\%

FPR95 on at least one domain, and the preferred detector depends on both the in-distribution data and the underlying VLM. We trace these reversals to complementary evidence channels in vision-language logits. Corpus-free detectors rely on different combinations of absolute match level and relative or spatial sharpness, while WordNet-based methods additionally depend on external semantic coverage. A simple proposition shows that level and sharpness cannot generally be recovered from one another, explaining why no single detector transfers reliably across deployments. Motivated by this diagnosis, we introduce the Complementary Evidence Guard (CEG), a detector-agnostic wrapper that preserves complementary evidence through a non-compensatory fusion of the base detector, level, and sharpness using only empirical in-distribution percentiles. Controls replacing these channels with entropy, logit variance, or random noise do not reproduce the gains. Without OOD samples, auxiliary corpora, or learned fusion, CEG reduces detector sensitivity and improves GL-MCM from

38.1

to

28.8

and MCM from

42.6

to

30.5

family-balanced FPR95.

Ignacio M. De la Jara, Cristian Rodriguez-Opazo, Stephen Gould +1

University of Adelaide · 3Naval Group Pacific · 2Australian National University

Out-Of-Distribution Detection In-Distribution Zero-Shot Robustness In-Domain Accuracy Sharpness-Aware Minimization Text Corpora

Jul 15, 2026cs.CV

Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study

Historical Manchu OCR must accommodate various visually distinct writing styles, including regular script, running script, and the semi-cursive chancery hand used in palace memorials, despite limited labeled data. We study a multi-expert system that reuses checkpoints from an iterative fine-tuning process as domain specialists and uses a lightweight page-level image classifier to dispatch pages by visual style. When the checkpoint pool lacks a suitable specialist, we train an additional expert for that domain. On three frozen test sets, the routed system matches the selected specialist for each style at two-decimal precision: 0.30 percent CER on regular script, 1.57 percent on memorials, and 4.83 percent on running script. The router achieves 99.3 percent page-level domain accuracy and matches the domain-label oracle at the same precision. Two of the three selected specialists were not trained specifically for their final domain; only the running-script expert was trained with that domain as its target. We report the evaluation protocol, router design, and per-page predictions to make the comparison reproducible.

Zhan Chen, Jiqiao Ma, Chih-wen Kuo

Institute of Advanced Studies, Beijing Normal University, Zhuhai, China · Faculty of Humanities and Social Sciences, Beijing Normal University–Hong Kong Baptist University United International College (UIC), Zhuhai, China · Independent Scholar +1

Optical Character Recognition Handwritten Text Recognition In-Domain Accuracy Handwriting Case Study

Jul 13, 2026cs.CV

MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration

Vision-language models (VLMs) such as CLIP enable zero-shot classification by comparing image features with text prompts in a shared embedding space. A fundamental property underlying this capability is the global comparability of logits across arbitrary candidate classes. However, VLMs are often adapted to fine-grained domains using techniques such as LoRA. While this improves in-domain accuracy, out-of-domain accuracy degrades. This leads to a highly fragmented model ecosystem, with thousands of specialized models. Multi-Expert-Domain classification seeks to address this problem, by merging LoRAs trained independently on specialized domains. However, due to the independent training, the various domain experts no longer produce globally calibrated logits. As a result, when evaluating over the union of multiple domain-specific class sets, heterogeneous logit scales induce cross-domain interference and artificially high confidence for out-of-domain classes, inducing prediction errors. In this work, we identify domain supervision and cross-domain logit miscalibration as the key issue to scalable multi-domain zero-shot recognition. We propose MED-DSLC, combining domain supervised training and domain-wise logit scaling, to explicitly restore global logit comparability. MED-DSLC is a lightweight solution for MED classification, which is shown to preserve within-domain discrimination while reducing cross-domain logit interference with minimal data. Extensive experiments across diverse fine-grained benchmarks demonstrate that it substantially improves mean accuracy (+15%), cross-domain robustness, and scalability in the size of MED classification problem. Our results show that restoring output-level calibration is essential under highly data imbalanced settings for achieving a truly zero-shot VLM under multi-domain specialization.

Zheng Zeng, Deepak Sridhar, Nuno Vasconcelos

University of California, San Diego, USA

Vision-Language Model Adaptation In-Domain Accuracy Logit Lens

Jun 28, 2026cs.AI

The Complexity Ceiling Benchmark: A Multi-Domain Evaluation of Sequential Reasoning Under Depth Scaling

We introduce the Complexity Ceiling Benchmark (CCB), a controlled evaluation of how language-model reasoning decays as the number of required sequential steps grows. CCB fixes the semantic content of a task and varies only its depth N in {5,...,50} across three structurally distinct regimes: grounded spatial state-tracking, abstract symbolic pointer manipulation, and transitive relational inference. Across 6,000 trials over five frontier and open-weight LLMs we find a consistent pattern of geometric per-step decay with widely separated domain ceilings: on the first two regimes the strongest models retain pd>0.92 across N=50; on the third every model collapses by N=5, with the best model's 50%-success horizon at H0.5~4.7 steps despite pd=0.863. A trace-level metric (TFBC) shows that 14.5% of correct answers across the benchmark are reached via incorrect intermediate reasoning. Forced verbose state-tracking does not move the ceiling (McNemar p=1.000), and the mean step at which reasoning first diverges, k*, predicts within-domain accuracy better than parameter count. CCB and the geometric decay model together reduce a model's long-horizon reasoning profile to one interpretable number per task family.

Shubh Chapra, Dhruv Kumar, Murari Mandal +1

BITS Pilani, Pilani Campus · KIIT Bhubaneswar

LLM Reasoning Strategies In-Domain Accuracy

Jun 19, 2026cs.SD

When EER Hides Deployment Failure: Auditing Threshold Transfer and Unlabeled Score Calibration for Speech Deepfake Detectors

Speech deepfake countermeasures (CMs) are compared almost exclusively by equal error rate (EER), a metric computed at an oracle threshold chosen on the labeled test set. Deployed CMs enjoy no such oracle: a threshold must be fixed in advance and applied to unlabeled target data. We audit this gap with a frozen state-of-the-art SSL-AASIST detector trained on ASVspoof 2019 LA. While its in-domain EER is 0.21%, transferring its LA-calibrated threshold to the In-the-Wild corpus yields a half total error rate (HTER) of 39.5%, with 78.7% of bona fide speech rejected, even though the In-the-Wild EER (11.2%) appears moderate. We then test whether popular unlabeled test-time corrections close this gap, and first prove a simple proposition: any strictly increasing score transform, including z-norm, temperature/shift calibration, and embedding mean alignment under a frozen linear head, cannot change EER. An audit of seven corrections on In-the-Wild and ASVspoof 2021 DF confirms the proposition empirically and exposes two further failure modes: AS-norm with an unlabeled target cohort collapses (EER 11.2% to 60.2%), and pseudo-label calibration that reduces HTER by 38% relative on In-the-Wild degenerates to 50% HTER on DF21, whose spoof prior is 96%. No audited correction reduces EER by more than 1% relative. We recommend reporting HTER at a transferred threshold alongside EER.

Jingwen Zhou, Mingzhe Wang

Xidian University, Xi’an, China

Equal Error Rate In-Domain Accuracy Pre-Deployment Safety Assessments

Jun 17, 2026cs.CL

Aligning Implied Statements for Implicit Hate Speech Generalizability with Context-Bounded Semi-hard Negative Mining

Classifying implicit hate speech remains a challenge, as intent is often masked through insinuation and context rather than explicit slurs. Prior supervised contrastive approaches improve in-domain detection but can overfit surface cues and struggle to transfer across datasets. We propose ImpSH, a triplet-based framework that aligns posts with implied statements when available and uses context-bounded semi-hard negatives to focus learning on near confusions. We also examine AugSH, which forms positives via data augmentation. In controlled evaluations on IHC, SBIC, and DynaHate with BERT and HateBERT, ImpSH is a viable alternative to standard supervised contrastive baselines and often improves cross-domain performance under matched preprocessing and tuning budgets. Representation analysis using alignment and uniformity indicates tighter positive pairs with balanced global spread, and qualitative nearest-neighbor case studies illustrate typical false negatives under domain shift. These results demonstrate that aligning posts with their implied statements via context-bounded mining provides a more stable, bijective-like mapping to related insinuations, overcoming the volatility inherent in traditional clustering-based representation learning.

Wicaksono Leksono Muhamad, Yunita Sari

Mantera Studio · Universitas Gadjah Mada

Hate Speech Detection Hate Speech Contrastive Learning Negative Results In-Domain Accuracy

Jun 14, 2026cs.CL

In-Domain Supervised Pathology Report Classification: A Reproducible Pipeline from Data Curation to Production-Matched Evaluation

We introduce an in-domain supervised pipeline designed to counter the out-of-distribution performance drop that hampers supervised biomedical NLP models, a problem observed when models trained on pathology reports are moved across cancer registries. Our contribution is a reproducible recipe for training a supervised classifier from routinely collected cancer registry data. It describes how to build the in-domain training set and a production-matched holdout, and to choose operating points that keep the false-negative rate (FNR) very low while keeping reviewer workload manageable. The pipeline standardizes data curation with facility-stratified sampling and separate handling of reports linked to registry cases, and includes a blinded manual audit to estimate positive-case prevalence and label noise. On a 418k-report holdout set, the Kentucky model achieved FNR 0.003 and false-positive rate (FPR) 0.097, improving over the Seattle-trained MOSSAIC OncoID baseline (FNR 0.010, FPR 0.183) and raising F1 from 0.860 to 0.922. In a blinded manual review of 600 reports, estimated positive prevalence declined from 0.500 to 0.398, indicating substantial label noise with errors concentrated in rare primary sites.

Isaac Hands, Bin Huang, Adam Spannaus +4

Department of Computer Science, University of Kentucky, Lexington, KY, USA · UK Markey Cancer Center, Lexington, KY, USA · Kentucky Cancer Registry, Lexington, KY, USA +3

False-Negative Rate In-Domain Accuracy Data-Curation Semi-Supervised Learning

Jun 8, 2026cs.LG

Stage-1 Controls the Entropy Regime, Not the Outcome

Two-stage post-training -- a Stage-1 warm-start (supervised fine-tuning, SFT, or on-policy distillation, OPD) followed by Stage-2 reinforcement learning (RL) -- is increasingly used for vision-language models (VLMs). We ask what Stage-1 actually controls in a small-data study using Qwen2.5-VL-7B with a same-modality 72B VLM teacher for OPD. First, the three warm-starts reach a narrow

53

--

54\%

band on Geometry3K internal validation, consistent with the narrow range reported by recent specialized methods; this setup provides little evidence that Stage-1 changes the in-domain endpoint. Second, a matched-recipe, early-stopped SFT improves out-of-domain MathVista by

+2.1

points, reversing the

-9.5

-point drop of an over-trained variant. The clearest difference is the \emph{entropy regime}: OPD enters RL with substantially higher policy entropy than either SFT initialization, and the separation remains visible through the available trajectories. At the in-domain initialization, OPD also has higher answer diversity and pass@16 (

+2.0

to

+5.2

points over SFT), although problem-level bootstrap intervals show that the smaller contrast is uncertain. The advantage is absent after RL (endpoint pass@16 values within

1.1

points) and on MathVista (six models within

1.2

points). Our contribution is therefore a bounded empirical characterization: Stage-1 is strongly associated with the entropy regime in this setup, but the downstream payoff is small, localized, and not evidence that OPD is a better RL warm-start.

Jianxiong Shen

Multi-Stage Training Warm Starts Qwen3 In-Domain Accuracy Offline Reinforcement Learning

May 27, 2026cs.CL

Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study

Large language models (LLMs) are increasingly used for the automatic evaluation of generated text, yet most prior work focuses on English. Despite the growing demand for multilingual evaluation, extending LLM-based evaluators to multilingual settings remains challenging, particularly for low-resource languages and scenarios where in-domain data is scarce. This work explores several strategies for developing multilingual LLMs-as-a-judge, considering whether in-domain data is available for fine-tuning or not. We systematically analyze English, Spanish, and Basque, representing high-, mid-, and low-resource languages, considering instruction translation, monolingual versus multilingual supervision, and model size. For evaluation, we extend two existing meta-evaluation datasets to Basque and Spanish. Our results reveal key trade-offs: When in-domain data is available, fine-tuned smaller models can achieve performance comparable to proprietary models, whereas zero-shot evaluation with larger models proves more effective in out-of-domain settings. We also observe that fine-tuning on out-of-domain data can adversely affect model performance. These findings provide practical guidance for building efficient, reliable multilingual evaluation pipelines. The data and code are publicly available at hitz-zentroa/mJudge.

Irune Zubiaga, Aitor Soroa, Rodrigo Agerri

HiTZ Center - Ixa, University of the Basque Country EHU

Multilingual Benchmark Large Language Model Evaluation Llm-As-A-Judge In-Domain Accuracy Empirical Study Reliable

May 8, 2026cs.LG

Rotation-Preserving Supervised Fine-Tuning

Supervised fine-tuning (SFT) improves in-domain performance but can degrade out-of-domain (OOD) generalization. Prior work suggests that this degradation is related to changes in dominant singular subspaces of pretrained weight matrices. However, directly identifying loss-sensitive directions with Hessian or Fisher information is computationally expensive at LLM scale. In this work, we propose preserving projected rotations in pretrained singular subspaces as an efficient proxy for Fisher-sensitive directions, which we call Rotation-Preserving Supervised Fine-Tuning (RPSFT). RPSFT penalizes changes in the projected top-

k

singular-vector block of each pretrained weight matrix, limiting unnecessary rotation while preserving task adaptation. Across model families and sizes trained on math reasoning data, RPSFT improves the in-domain/OOD trade-off over standard SFT and strong SFT baselines, better preserves pretrained representations, and provides stronger initializations for downstream RL fine-tuning. Code is available at \href{https://github.com/jinhangzhan/RPSFT.git}{https://github.com/jinhangzhan/RPSFT}.

Hangzhan Jin, Tianwei Ni, Lu Li +3

1Mila - Quebec AI Institute · 2Polytechnique Montréal · 3Université de Montréal +3

Model Fine-Tuning Subspace In-Domain Accuracy

May 7, 2026cs.CL

Lightweight Stylistic Consistency Profiling: Robust Detection of LLM-Generated Textual Content for Multimedia Moderation

The increasing prevalence of Large Language Models (LLMs) in content creation has made distinguishing human-written textual content from LLM-generated counterparts a critical task for multimedia moderation. Existing detectors often rely on statistical cues or model-specific heuristics, making them vulnerable to paraphrasing and adversarial manipulations, and consequently limiting their robustness and interpretability. In this work, we proposeLiSCP , a novel lightweight stylistic consistency profiling method for robust detection of LLM-generated textual content, focusing on feature stability under adversarial manipulation. Our approach constructs a consistency profile that combines discrete stylistic features with continuous semantic signals, leveraging stylistic stability across multimodal-guided paraphrased text variants. Experiments spanning real-world multimedia news and movie datasets and conventional text domains demonstrate that LiSCP achieves superior performance on in-domain detection and outperforms existing approaches by up to 11.79% in cross-domain settings. Additionally,it demonstrates notable robustness under adversarial scenarios, including adversarial attacks and hybrid human-AI settings.

Siyuan Li, Aodu Wulianghai, Xi Lin +6

School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China · College of Computer Science and Technology, Zhejiang University, Hangzhou, China

Content Moderation Human-Written Text Stylistic Fidelity Large Language Model Hallucination Text Analysis and Detection In-Domain Accuracy

Apr 29, 2026cs.CV

Cross-Domain Transfer of Hyperspectral Foundation Models

Hyperspectral imaging (HSI) semantic segmentation typically relies on in-domain training, but limited data availability often restricts model performance in real-world applications. Current approaches to leverage foundation models in proximal sensing use cross-modality techniques, bridging RGB and HSI to exploit vision foundation models. However, these methods either discard spectral information or introduce architectural complexity. We propose cross-domain transfer as an alternative, reusing HSI foundation models - originally trained in remote sensing - for proximal sensing applications. By eliminating the need to bridge modality gaps, our approach preserves spectral information while maintaining a simple architecture. Using the HS3-Bench benchmark, we systematically evaluate and compare conventional in-domain, in-modality training, cross-modality transfer and cross-domain transfer strategies. Our results demonstrate that cross-domain transfer achieves large performance improvements over in-domain, in-modality training, reduces the performance gap to cross-modality approaches and maintains strong performance in limited data settings. Thus, this work advances more effective HSI semantic segmentation in diverse applications.

Nick Theisen, Peer Neubert

Intelligent Autonomous Systems, University of Koblenz, Germany

Hyperspectral Image Cross-Modality Recent Vision Foundation Models Semantic Segmentation In-Domain Accuracy Foundation Model

Apr 24, 2026cs.CL

EverydayGPT: Confidence-Gated Routing for Efficient and Safe Hybrid GPT-RAG Conversational QA

Standard Retrieval-Augmented Generation (RAG) pipelines route every query through retrieval and generation unconditionally, incurring unnecessary computation and propagating low-quality context to the generator. We introduce EverydayGPT, a lightweight conversational QA system built around a Confidence-Gated Routing (CGR) mechanism that formalises the routing decision as a joint policy over retrieval distance and extraction adequacy. The backbone is a 205M-parameter GPT trained from scratch on 10B tokens of FineWeb-Edu. CGR avoids invoking the costly GPT pathway (~5.9s) for 85 percent of queries by resolving them via fast RAG extraction (~45 ms), yielding over 120x latency reduction on the majority of queries while maintaining answer quality. On a 500-question in-domain benchmark, the system achieves F1 = 0.226 +/- 0.004 compared to 0.171 for GPT-only and 0.210 for unconditional RAG. Gains over strong baselines are modest but consistent, while efficiency improvements are substantial (6.3x mean latency reduction). A structured grounding audit finds no unsupported claims in the sampled set, with explicit scope limitations. We position this work as a study of routing strategies under resource constraints rather than a claim of state-of-the-art performance.

Jaspreet Singh Nahal

B.Tech Computer Science Engineering (Artificial Intelligence) Dr. A.P.J. Abdul Kalam Technical University, Delhi, India

Hievi-Rag Gating In-Domain Accuracy

Apr 21, 2026cs.AI

CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation

Large language models (LLMs) have achieved substantial advances in logical reasoning, yet they continue to lag behind human-level performance. In-context learning provides a viable solution that boosts the model's performance via prompting its input with expert-curated, in-domain exemplars. However, in many real-world, expertise-scarce domains, such as low-resource scientific disciplines, emerging biomedical subfields, or niche legal jurisdictions, such high-quality in-domain demonstrations are inherently limited or entirely unavailable, thereby constraining the general applicability of these approaches. To mitigate this limitation, recent efforts have explored the retrieval of cross-domain samples as surrogate in-context demonstrations. Nevertheless, the resulting gains remain modest. This is largely attributable to the pronounced domain shift between source and target distributions, which impedes the model's ability to effectively identify and exploit underlying shared structures or latent reasoning patterns. Consequently, when relying solely on raw textual prompting, LLMs struggle to abstract and transfer such cross-domain knowledge in a robust and systematic manner. To address these issues, we propose CoDA, which employs a lightweight adapter to directly intervene in the intermediate hidden states. By combining feature-based distillation of CoT-enriched reference representations with Maximum Mean Discrepancy (MMD) for kernelized distribution matching, our method aligns the latent reasoning representation of the source and target domains. Extensive experimental results on multiple logical reasoning tasks across various model families validate the efficacy of CoDA by significantly outperforming the previous state-of-the-art baselines by a large margin.

Jianzhi Yan, Le Liu, Buzhou Tang +3

Harbin Institute of Technology, Shenzhen, 518100, China · Pengcheng Laboratory, Shenzhen, 518100, China

LLM Reasoning Strategies In-Domain Accuracy Domain Adaptation In-Context Learning

Apr 19, 2026cs.CL

Bidirectional Small-Granularity Search between Code and Text

We introduce the novel task of bidirectional small-granularity search between code and text, where the queries are small snippets of text or code and the results are also small fragments of the opposite modality, i.e., code or text. This task establishes direct links between text in scientific publications and corresponding code segments, in support of better and faster understanding of scientific methods. We introduce a large dataset for the proposed task that includes a training partition with textual descriptions of code generated automatically using GPT-4, and three testing partitions, one in-domain and two out-of-domain (OOD) that contain manually-annotated data as well as material from other domains. We also propose a modular approach to address this task. Our approach shares an encoder across four different subtasks that learn start/end of answer spans in both directions. We show that our method achieves good results in-domain, and encouraging results OOD. This suggests that addressing this task with automatically-generated data is possible, but there is exciting future work to be done.

Marco A. Valenzuela-Escárcega, Enrique Noriega-Atala, Gus Hahn-Powell +2

Lex Machina · The University of Arizona, Tucson, AZ, USA

Text Analysis and Detection In-Domain Accuracy

May 7, 2025cs.CV

Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions

Functional grasping is essential for enabling dexterous multi-finger robot hands to manipulate objects effectively. Prior work largely focuses on power grasps, which only involve holding an object, or relies on in-domain demonstrations for specific objects. We propose leveraging human grasp information extracted from web images, which capture natural and functional hand-object interactions (HOI). Using a pretrained 3D reconstruction model, we recover 3D human HOI meshes from RGB images. To train on these noisy HOI data, we propose to use: (1) an interaction-centric model to learn the functional interaction pattern between hand and object, and (2) geometry-based filtering to remove the infeasible grasps and physical simulation to retain grasps who can resist disturbance. In IssacGym simulation, our model trained on reconstructed HOI grasps achieves a 75.8% success rate on objects from the web dataset and generalizes to unseen objects, outperforming baseline methods in both grasp success and functional quality. In real-world experiments with the LEAP hand and Inspire hand, it attains a 77.5% success rate across 12 objects, including challenging ones such as a syringe, spray bottle, knife, and tongs. Project website is at: https://web2grasp.github.io/.

Hongyi Chen, Yunchao Yao, Yufei Ye +8

Carnegie Mellon University · Nvidia · National University of Singapore +1

Robotic Grasping Query Image In-Domain Accuracy