GitHub Issues ·
`Trainer.evaluate` eval_loss under DDP includes the samples the sampler repeats to even out the last batch
Public issue #49979 in huggingface/transformers. The source issue contains the full report and discussion.
Home / Browse
All stories
Browse every indexed public story, including items outside the main categories.
9972 public stories
GitHub Issues ·
Trainer scales the loss of heads that take `**kwargs` but return a mean loss by `world_size * gradient_accumulation_steps` (BERT family, BART/T5, ...)
Public issue #49978 in huggingface/transformers. The source issue contains the full report and discussion.
Hacker News ·
Local-first video production workspace for people and AI agents
Submitted by jev-yeb. Hacker News recorded 3 points and 0 comments as of Oct 26, 2026 (UTC).
GitHub Discovery ·
andyhuo520/digital-human-koubo
AI digital-human talking-head videos from one photo: Renoise MCP generation + 5 editing styles + 48 creator-grade packaging components. Agent skill for Claude Code / Codex / OpenClaw / WorkBuddy …
arXiv ·
Validating the Comparison, Not Just the Scorer: Why Overall Accuracy Can Mislead in Interactive LLM Evaluation
arXiv:2610.31678v1 Announce Type: new Abstract: Many LLM studies compare how models respond to different follow-up prompts. For example, one prompt may neutrally ask a model to reconsider, while another insists that an invented film really exists. The difference is used to measure the effect of conversational pressure. An automatic scorer then labels whether each response makes an unsupported factual claim. Researchers commonly validate the scorer with one overall accuracy or $F_1$ score. Howeve
arXiv ·
MisconceptDialogue: Evaluation Criteria Shape Measured Success in LLM Math Tutoring
arXiv:2610.31679v1 Announce Type: new Abstract: Large language models are increasingly used as math tutors, raising two questions: can a single LLM detect a student's error, diagnose the underlying misconception, and remediate it through multi-turn dialogue - and can we trust the numbers that report how well it does? We address both with MISCONCEPTDIALOGUE, a fully automated framework that runs the full pipeline on five open-weight LLM tutors (7B-14B) interacting with LLM-simulated students over
arXiv ·
Rethinking Structured Generation: Can Graph-Based Reasoning Resolve Ambiguity?
arXiv:2610.31681v1 Announce Type: new Abstract: Structured generation is typically formulated as a deterministic mapping from input to a single structured output. This assumption is fundamentally misaligned with natural language, which often admits multiple structurally distinct yet semantically valid interpretations. As a result, existing methods rely on single-reference supervision that collapses ambiguity into one prediction, leading to unstable and inconsistent outputs under underspecified i
arXiv ·
Multi modal perceived conversation success prediction for spontaneous autistic and non-autistic dyadic interactions
arXiv:2610.31682v1 Announce Type: new Abstract: Conversation success is important for communication, social bonds, and well-being and is often reduced in autistic-neurotypical conversations. Previous studies have predicted perceived conversation success using acoustic and lexical features in pediatric autism-enriched samples, or using nonverbal behavior in non-autistic group interactions. Other work has characterized prosodic, facial, motor, and turn-taking synchrony in autistic interactions, bu
arXiv ·
The Schema Coherence Inventory: Measuring Whether an Assigned Belief Organizes a Language Model's Cognition
arXiv:2610.31683v1 Announce Type: new Abstract: Persona-conditioned language models are used as simulated patients and affective agents, but there is no validated way to ask whether a belief assigned to such a model organizes its behaviour or whether the model has merely adopted a mood. We present the Schema Coherence Inventory (SCI): 96 forced-choice items at eight levels of Beck's cognitive model, each offering six replies keyed to three negative self-schemas and their positive counterparts, s
arXiv ·
Knowledge Graphs Quality Assessment in the Era of LLMs: A Conceptual Framework
arXiv:2610.31684v1 Announce Type: new Abstract: Knowledge Graphs (KGs) have been popularized during the last few decades and are increasingly constructed and consumed by Large Language Models (LLMs). Various applications therefore rely on KGs to provide concise, complete, accurate, faithful, fresh, and traceable answers. However, what is the quality of those KGs? In which cases should a KG be used, and can it be trusted to ground an LLM? How might it be evaluated? We reviewed the literature on q
arXiv ·
An Agentic Approach with Evidence-Grounded Verification for Multimodal Emotion Reasoning in Conversation
arXiv:2610.31685v1 Announce Type: new Abstract: LLM-based multimodal emotion reasoning systems perform well on standard benchmarks, but improving them through instruction tuning can be computationally expensive. Agentic pipelines built from frozen models avoid this cost, but introduce a different challenge: when a prediction is wrong, the system must identify which agent or stage caused the error. We address this problem with an agentic framework for traceable multimodal emotion reasoning and pr
arXiv ·
From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models
arXiv:2610.31686v1 Announce Type: new Abstract: Activation interventions can make a language model produce a target answer, but can the model use the intended condition in other computations? We study this question in Qwen3.5-27B on tool-use tasks where time or permissions determine eligibility and selection. Across 32 fresh worlds, two case-specific residual-writing variants raise familiar target-selection correctness from 35/128 to 119/128 and from 33/128 to 114/128. Yet these gains disappear
arXiv ·
Distributional Alignment of LLMs and Its Generalization Properties
arXiv:2610.31687v1 Announce Type: new Abstract: Large language models are increasingly used to simulate and probe human behavior, e.g., for surveys. For these applications, a key property is that outputs satisfy distributional alignment: to match its output distribution with some reference (in this case, human) distribution. An obstacle in achieving distributional alignment is generalizing from small training data. In this work, we study (1) how to distributionally align LLMs; and (2) how aligne
arXiv ·
LAMB: A Modern Contextual Language Model for Latin
arXiv:2610.31723v1 Announce Type: new Abstract: This article introduces Latin Modern BERT (LAMB), an encoder for the Latin language based on the ModernBERT architecture, pretrained in two phases on more than 74B Latin tokens using a novel morphologically informed masking regimen. We also present two corpora for the Latin language. Acervus contains 24B BERT WordPiece tokens, including over 760K samples from heavily damaged OCR transcriptions, repaired by a ByT5 model trained for Latin text repair
arXiv ·
Free Lunch for LLMs Confidence: The RL Critic Already Knows
arXiv:2610.31820v1 Announce Type: new Abstract: Reliable confidence estimation is essential for trustworthy deployment of large language models (LLMs), but dedicated confidence training stage requires additional data and compute. We ask a fundamental question: what prediction problem does confidence training actually solve? Inspired by prior work on external confidence estimation, we compare self- and external estimators of comparable capacity trained on the same (question, response, correctness
arXiv ·
What the Query Remembers: Query Abstraction Governs Lexical and Dense Retrieval of Classical Arabic Poetry
arXiv:2610.31821v1 Announce Type: new Abstract: How well a poetry archive can be searched depends on what the user still remembers, not only on what the model understands. We show this for Classical Arabic poetry, benchmarking nine dense encoders and BM25 over two corpora, three indexing modes and two evaluation protocols. Which retriever wins is governed by how much of a poem's wording the query still carries. On tip-of-the-tongue queries BM25 leads every dense encoder, including an 8B state-of
arXiv ·
Latent Coherence: Do Frontier Language Models' Probability Judgments Obey the Law of Total Probability?
arXiv:2610.31833v1 Announce Type: new Abstract: LawZero's Scientist AI trains a Predictor toward the Bayesian posterior, with an objective that penalizes inconsistent probabilities among latent explanations. We ask whether current frontier language models, with no such training, are already consistent in this sense zero-shot: do their probability judgments satisfy the law of total probability, $P(X)=\sum_z P(z)P(X|z)$, when the latent $z$ must be inferred from records in the context? In separate
arXiv ·
SAGE: Sense-Aligned Multimodal Grounding Evaluation with Gloss-Augmented Reasoning
arXiv:2610.31838v1 Announce Type: new Abstract: This paper introduces Sense-Aligned Grounding Evaluation (SAGE), a unified 10-candidate image-selection benchmark that reformulates VWSD, VerSe, and WikiDiverse into a shared term-centric protocol covering noun-, verb-, and entity-centered grounding. SAGE includes confusable hard negatives and a context-swapped VerSe diagnostic to probe target-term grounding beyond direct caption--image compatibility. We further propose Gloss-Augmented Reasoning (G
arXiv ·
SPECMEM: Accelerating Agentic Tool Calling via Live Memory Management
arXiv:2610.31840v1 Announce Type: new Abstract: Tool-calling agents are mostly optimized for accuracy; in deployment, however, their growing cost is latency: every tool call is decoded autoregressively. Speculative decoding accelerates this without changing the output, and retrieved past calls make strong drafts under real use, where each user's behavior tends to repeat. Yet existing systems keep no cross-session memory, or build the draft store once and never update it. We propose SpecMem, a to
arXiv ·
Scaling cross-situational word learning on children's naturalistic experiences
arXiv:2610.31842v1 Announce Type: new Abstract: How do children learn the meanings of the simple, concrete words that form a majority of their early vocabulary? Statistical information about many word meanings can be recovered from the gradual accumulation of information about the co-occurrence of words with their referents, a proposal known as ``cross-situational learning''. Contrastive vision--language models allow this learning strategy to be tested on egocentric video data capturing children
arXiv ·
Machine-Readable Operator Manuals over the ISO 11783 Network for Offline, Multilingual LLM Assistance
arXiv:2610.31863v1 Announce Type: new Abstract: If agricultural machinery is to support intelligent, offline assistance, then the system must access technical documentation dynamically. In this paper, the Semantic Synchronization of operator manuals over ISO 11783-based CAN buses is analyzed, defined as the process that brings the local knowledge base of a tractor-side assistant into agreement with the operator manual of the connected implement. Data transfer performance was benchmarked using Ma
arXiv ·
Mining Frames: Association Rule Mining as an Unsupervised Framework for News Framing Detection
arXiv:2610.31874v1 Announce Type: new Abstract: Computational framing analysis is dominated by supervised classifiers that require large annotated corpora and predefined frame taxonomies, limiting their use for non-English languages, novel events, and low-resource settings. This paper presents Association Rule Mining (ARM) as an unsupervised, annotation-free framework for news framing detection. Each document or sentence is treated as a transaction of lexical items, and high-lift co-occurrence r
arXiv ·
TaxoSAE: Rethinking Sparse Autoencoders through Taxonomic Logic
arXiv:2610.31894v1 Announce Type: new Abstract: Recent Sparse Autoencoders (SAEs) decompose the representations of large language models (LLMs) into interpretable features, enabling precise readout and control of encoded knowledge. However, existing SAEs treat each feature as a standalone unit, whereas real-world knowledge is often taxonomically organized. As a result, readout carries no guarantee of taxonomic consistency, and control lacks the granularity to specify the scope of an edit. We pro
arXiv ·
LazyFlash: Forward-Dense, Backward-Sparse Attention for Accelerated Long-Context Fine-Tuning
arXiv:2610.31911v1 Announce Type: new Abstract: As large language models (LLMs) process increasingly long sequences, attention becomes a major computational bottleneck. Sparse attention mostly targets inference, yet many methods still train densely or cannot support sparse training, and their added complexity makes sparsity hard to turn into wall-clock speedups, leaving dense attention widely used in practice. This paper introduces LazyFlash, a forward-dense, backward-sparse attention method bui
arXiv ·
Kolibri: A Sovereign European Model on the Pareto Frontier
arXiv:2610.31945v1 Announce Type: new Abstract: This report introduces Kolibri, an English-German mixture-of-experts transformer with 78.1B total parameters and 3.46B active parameters per token, released as open weights under the Apache 2.0 licence. We built Kolibri for sovereign and specialised deployment, with a particular focus on German and on regulated domains such as public administration, industry, and aerospace. To support these settings, we control the full model-development process, i
arXiv ·
Which Answer Did the Seventeen-Year-Old Write? A Behavioral Case Study of Author-Age Misattribution, Miscalibrated Confidence, and Non-Corrective Self-Explanation in Six Frontier Language Models
arXiv:2610.31946v1 Announce Type: new Abstract: Three students answered the same exam prompt by hand: "What is happiness? Are you happy?" Their ages, recorded at collection, are 17, 28, and 45. The 17-year-old's answer is hedged and formally phrased. Asked to match each answer to an age and gender label, most frontier language models confidently assign it to an adult. This paper reports a structured case study of that failure across six models: Claude Fable 5, Gemini 3.1 Pro, GPT-5.6 Sol, Grok 4
arXiv ·
POS-Signature Demonstration Retrieval for In-Context Dependency Parsing
arXiv:2610.31966v1 Announce Type: new Abstract: Demonstrations for in-context learning are often retrieved by semantic similarity, which may be a poor proxy for relevance in structured prediction. We study demonstration selection for Universal Dependencies parsing with a POS-signature policy that represents sentences with weighted part-of-speech statistics and retrieves three length-compatible, gold-parsed examples from the labeled training split. We evaluate two open-weight language models with
arXiv ·
DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation
arXiv:2610.32002v1 Announce Type: new Abstract: The rapid growth of microdramas has increased demand for high-quality script production. Long-form microdrama script generation with LLMs requires both diverse plot progression and long-range narrative coherence. Our observations reveal that candidate continuations increasingly concentrate on fewer narrative mechanisms as generation progresses, while conventional retrieval may reinforce trope reuse and overlook historical information essential to f
arXiv ·
X-Dubbing: Speech-to-Speech Translation under Temporal and Visual Constraints
arXiv:2610.32042v1 Announce Type: new Abstract: Cross-lingual dubbing aims to convert source speech into target-language speech that remains synchronized with the original video. The key to this task is to produce a faithful translation that is naturally speakable within the source timing, which is non-trivial because languages differ in duration, rhythm, and articulation. In this paper, we propose X-Dubbing, which formulates the task as a joint problem of time-aware speech-to-text translation a
arXiv ·
How Much Do You Trust A Dog? Quantifying Hint-Following in Reasoning Language Models
arXiv:2610.32055v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit sycophancy, altering their answers to align with user suggestions even on objective factual and reasoning tasks. Yet the quantitative form of this influence--- and whether it is calibrated to source reliability--- remains poorly understood. In this work, we investigate this behavior through hint-induced answer shifts on MMLU questions, evaluating prompts of the form ``[Source] thinks the answer is (X)''. W