TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

Research · AI field

Frontier LLMs

The largest general-purpose language models, their releases, capabilities, scaling and training at frontier scale.

Field page: people, tools, topics →
478papers this week−0.2% vs last week2174 this month

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI
Fields · this week
All fields3737Multimodal591Agents557Frontier LLMs478Inference & serving288Image segmentation188Graph learning182Learning verifiable rewards1733D scene169Evals108Voice AI102Classifier & causal discovery88Forecasting time86Flow matching84Training & fine-tuning64Teacher policy distillation58All 32 fields
WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems in Frontier LLMs

  • Structural requirements for decision-native models1 paper raises it · 1 addresses it

    Current decision models often ignore key properties like null-awareness, permutation invariance, and option scalability, limiting their reliability and efficiency.

    • Jeva: System One Models from First Principlesraises · addresses
  • Efficient and calibrated decision-making for search agents1 paper raises it · 1 addresses it

    Generative models introduce latency and unreliable confidence in short, repeated decisions, hindering real-time search agent performance.

    • SearchJev: A Fast and Calibrated System-1 Model for Search Agentsraises · addresses
  • Sustaining self-evolution in reasoning models1 paper raises it · 1 addresses it

    Self-training on generated questions can collapse performance due to invalid or repetitive questions, limiting long-term improvement.

    • Questioning the Questions: Sustaining Self-Evolution in Reasoning Modelsraises · addresses
  • Memory consolidation in context-conditioned models1 paper raises it · 1 addresses it

    Gains from context are often lost after its removal, reducing the long-term utility of contextual learning.

    • Cortex: Consolidating Context into Parametric Memoryraises · addresses
  • Detecting and mitigating scientific slop in AI-generated papers1 paper raises it · 1 addresses it

    AI-generated scientific papers can appear plausible but contain flawed reasoning, misleading readers and degrading research quality.

    • Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papersraises · addresses

Named by an AI from these papers' abstracts.

Rising research topics

Coming with more sources: more tagged papers
  • Federated learning50+38.9%
  • Agents557+7.9%
  • Frontier LLMs478−0.2%
  • Forecasting time86−5.5%
  • Inference & serving288−6.2%
  • 3D scene169−9.6%
  • Image segmentation188−10.9%
  • Sensing communication14−12.5%

Papers

  • arXiv cs.CVOct 20

    PsycheMME: A Psychology-Informed Benchmark for Social Understanding and Interaction in Videos

    Heran Hu, Yuhang Dong, Zhucun Xue, Kaiwei Chen, Yong Liu +1

    Understanding human needs and selecting responses require distinct judgments that aggregate accuracy can obscure. We introduce PsycheMME, a video benchmark informed by psychology, with eight capabilities spanning grounding, states, needs, interaction decisions, memory, and risk. Drawing on Social Information Processing and the Perception-Action Cycle, this organization separates human understanding from response selection. We construct 1,000 questions from 630 episodes through independent answering with proposed references withheld and expert review. Our Reasoning-Verified protocol weights answer credit by the support and logical consistency of explicit rationales against annotated cues. Across 17 models, Timing has the lowest Verified scores and credit retention, with weaker support judgments for correct Timing answers. Models with similar Need scores still differ in answer completeness on open questions. Input controls and SFT/GRPO examine context dependence and adaptation. Evaluating answers alongside rationales locates where models fail across understanding, response selection, and justification.

    PDF
  • arXiv cs.CLOct 20

    Benchmarking Arabic Dialects for Math Problems

    Noor Abo Mokh, Teresa Lynn, Nizar Habash, Ahmed Elshabrawy, Sara Alhajeri +3

    Mathematical reasoning remains underexplored for low-resource languages, including Dialectal Arabic. To bridge this gap, we introduce the DAR-MGSM (Dialectal Arabic Multilingual Grade School Math) Benchmark, the first manually curated benchmark for evaluating mathematical reasoning in Dialectal Arabic. DAR-MGSM consists of math word problems (MWPs) requiring multi-step reasoning and covers five major Arabic dialects alongside Modern Standard Arabic (MSA). The benchmark comprises two parallel versions: translated-only and translated & culturally localized. The latter version adapts entities and references to regional varieties. We evaluate eleven Arabic-centric and multilingual large language models on DAR-MGSM. The results show that the performance generally declines on the localized version, highlighting the challenges introduced by culturally grounded adaptations. However, the magnitude of this effect varies across models, with Arabic-centric models exhibiting different levels of sensitivity to localization. A mechanistic interpretability analysis shows that translated and localized variants of the same MWPs often induce distinct internal reasoning trajectories, even when…

    PDF
  • arXiv cs.AIOct 20

    Value-Rich, Differently Organized: Measuring Value Expression and Organization in AI-Generated Debates

    Maoyuan Li, Haoyuan Li, Zhongsheng Wang, Jiamou Liu

    Current evaluation of LLM-generated debate largely focuses on argumentative quality, leaving the value structure of generated arguments underexamined. We introduce a diagnostic metric framework for comparing how values are expressed and organized in human-reference and AI-generated debates. The framework separates value expression, the range of recognizable values a debate invokes, from value organization, how those values are distributed and sustained across turns. Grounded in Schwartz's Basic-10 value theory, it represents debates as multi-level value distributions over argumentative units, utterances, stances, and full debates, enabling metrics for value coverage, alignment, diffusion, and cross-turn dynamics. Across multiple generation systems, AI-generated debates are broadly value-expressive, often activating as many or more value dimensions than matched human references, but they organize these values differently. Their utterances are more locally value-diffuse, and source-blind judges distinguish value clarity from value focus. These findings show that debate evaluation should consider not only value presence, but also value organization. Code and supplementary materials…

    PDF
  • arXiv cs.AIOct 20

    Beyond the Sequentiality Bottleneck: A Hybrid Diffusion-Autoregressive Framework for Efficient Multimodal Reasoning

    Wei Cai, Jian Zhao, Yuchen Yuan, Xuelong Li

    Autoregressive models (ARMs) face a "Sequentiality Bottleneck" in reasoning, while diffusion language models (DLMs) offer parallelism but lack semantic coherence. To addresses both limitations, we propose Collaborative Reasoning Asymmetric Learning (CoRAL), a hybrid framework via an Asymmetric Planner-Executor (APE) architecture: a DLM Planner generates K diverse reasoning trajectories in parallel, while a large ARM Executor selects the optimal plan and synthesizes the final answer. To train the Planner effectively, we introduce Reward-Guided Denoising for CoT (RDC), which integrates outcome-based rewards into the diffusion process to steer it toward goal-directed reasoning. Experiments on vision-language benchmarks show that CoRAL significantly outperforms prior diffusion-based methods and achieves competitive performance against strong ARMs, achieving both superior efficiency and quality.

    PDF
  • arXiv cs.AIOct 20

    Evolving Semantic Indexes for Generative Retrieval

    Jinming Nian, Jyun-Yu Jiang, Henry Tsai, Yi Fang, Zhirong Liang

    Generative retrieval (GR) casts search and recommendation as autoregressive generation of discrete semantic identifiers (SIDs). SID design largely determines GR quality, but its discrete, interdependent components (SID construction, collision handling, decoding, and training) cannot be optimized end-to-end with gradients and remain largely hand-designed. We introduce a framework that improves these components through LLM-driven evolutionary program search, to our knowledge the first application of this approach to GR. A locally served, open-weight 31B model mutates executable GR components, so no proprietary LLM API is used, and a 1M-parameter proxy decoder provides fast feedback in place of repeatedly training the 1B target generator. Across 21 SID programs on NQ320K, proxy and target Recall@100 show strong rank correlation (Spearman $ρ= 0.90$). Guided by this proxy, evolution improves the seed GR on NQ320K, MSMARCO300K, and a multilingual e-commerce dataset under a fixed training recipe. On NQ320K, jointly evolving SID construction and collision handling improves Recall@1 from 55.8% to 59.3% and Recall@100 from 85.8% to 90.6%. A component study shows that proxy reliability…

    PDF
  • arXiv cs.CVOct 20

    Predictive Latents for Autoregressive Language Models: Possibility, Gauge, and Obstruction

    Yuzhou Hong

    Autoregressive language models are trained by next-token cross-entropy, yet several recent systems also iterate a hidden state without emitting a token: continuous thoughts, pause steps, and recurrent depth. This note separates three risks on one latent process. The token risk $R_{\mathrm{tok}}$ scores a readout. The teacher-forced latent risk $R_1$ scores a one-step map that sees the true hidden state. The open-loop risk $R_H$ scores the same map after it has been iterated on its own outputs. If the Bayes next-token posterior is a function of a $k$-dimensional statistic with full-rank covariance, a width-$k$ latent, a linear least-squares transition, and a refit unembedding match the Bayes token predictor. The statistic is identified only up to an invertible gauge: whitening the residual stream does not change the token law once the unembedding is refit. The matching obstructions are sharp. A constant latent drives $R_1$ to zero while token cross-entropy falls back to the marginal entropy. A perfect token predictor can still hide a null-space walk whose open-loop error grows linearly in the horizon. A small next-latent loss does not certificate next-token prediction, and a small…

    PDF
  • arXiv cs.AIOct 20▲ 1

    DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems

    Xialie Zhuang, Mingcong Lei, Zunhai Su, Ri Liu, Jianjin Li +5

    Decision models support routing, guardrails, and output verification in LLM systems. However, item accuracy alone cannot establish whether models make correct decisions across controlled variations or assign reliable confidence to their predictions. We introduce DecisionPivot, a diagnostic benchmark comprising 48 tasks and 40,033 items across seven decision roles. Its core track contains 7,800 items from 13 generated task families, organized into contrast groups with computed answers verified by independently implemented solvers. The complementary reference track contains 32,233 items from 35 public test sets, preserving their original evaluation metrics. We evaluate 40 decision models and 14 general models using documented, model-specific protocols, assessing item and contrast-group accuracy, probability ordering, calibration, and empirical selective coverage. Our results reveal substantial differences obscured by aggregate scores: two 27B models separated by only 2.6 points on the reference track achieve contrast-group accuracies of 70.1% and 44.2%. Across 2,400 binary contrast pairs, Perplexity Decider correctly ranks the positive member above the negative member in 92.3% of…

    Code
  • arXiv cs.LGOct 20

    Present but Hard to Read: Probing Latent Reasoning with Minimal Pairs

    Aur Shalev Merin

    Probing studies of latent reasoning often read a model's state where the answer begins and take a failed probe as evidence that a value is absent. We test this with a digit copied from the question, in the looped model Ouro-1.4B and the standard transformer Qwen2.5-1.5B. Comparing prompts that differ only in that digit shows it is present at the last prompt token, in a code shared across questions (readout about 0.9). A probe that sees one prompt at a time, the usual setting, barely reads it: 0.36 in Ouro and 0.19 in Qwen even after 5,249 training questions. The digit's change is small rather than crowded: random noise lands on equally busy directions, while a random word in its place moves the state far more and is readable. Since every varied token leaves a trace, a successful probe is ambiguous too. We give a protocol, including a synthetic null for generic mixing, for testing computed values against copies and mixtures of the inputs. In pre-registered studies of two-step problems it finds a small signal for the unwritten intermediate a+b just before Ouro writes the answer's last digit, and its sign follows the operation, though mixing alone produces much of that…

    PDF
  • arXiv cs.CVOct 20

    Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training

    Zhizhuo Kou, Heming Li, Jian Yang, Junyu Luo, Jingshu Peng +2

    People adapt how they talk to the person in front of them. However, chat models tend to respond in Standard English regardless of the dialect used by the user. A uniform answer can hide whether training treats these users alike, and output audits cannot tell as well. We trace how each post-training stage, from supervised fine-tuning (SFT) to preference optimization (DPO) and reinforcement learning, changes a model's tendency to match the user, and read what each update prefers from two content-matched replies, one matching the user and one not. Across 10 open model lineages, post-training standardizes replies to every informal cue, yet after adjusting for how likely each reply already was, the DPO update still favours matching British and Australian spelling over AAE and Singlish on 10 lineages, and models still produce AAE features when asked. We then introduce calibrated accommodation pairs (CAP), preference data that reward matching users' dialect density while preserving Standard English for Standard-English users. On a fully open model, CAP raises convergence on features it was not trained on without a detectable increase in dialect for Standard-English users or a cost in…

    PDF
  • arXiv cs.CLOct 20

    MythoSemantic: An Interactive System for Discovering Semantic Parallels Across Mythological and Religious Traditions

    Nikita Ganziuk, Innokentiy S. Humonen, Ilya Makarov, Pavel Lebedev

    We present a tool for the comparative study of mythological and religious texts. Traditional manual analysis is highly labor-intensive and difficult to scale. To address this, we use neural language models to embed texts into a shared semantic space, so that users can find semantic parallels across cultural traditions in an interactive interface. Embedded fragments form distinct semantic structures whose coarse geometry aligns with well-documented historical relations between traditions. We quantify how much of that geometry is already explained by lexical overlap and by proper names. The current system is available at https://mythoscope.io, and the installable package is available at https://github.com/haafus/MythoSemantic/blob/main/RUN.md.

    PDF
  • arXiv cs.CLOct 20

    Every Model Leaves a Trace: Multi-Resolution LLM Fingerprinting

    Mohammad Reza Modarres, Armin Tourajmehr, Artin Tavasoli, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar

    Large language models leave model-specific traces in their generated text, but it remains unclear how finely these fingerprints can distinguish related models and which signals remain informative as obvious cues are reduced. We study this through fingerprint resolution, considering both model resolution, from different families to distilled and adapted variants, and signal resolution across behavioral, stylometric, lexical, and semantic evidence. We progressively suppress surface cues, paraphrase outputs, vary the amount of available text, and test generalization across prompt distributions and languages. Our results show that fingerprints persist beyond broad family differences, remaining detectable in distilled models and even LoRA adaptations of the same base model. Although attribution weakens as surface and lexical cues are altered, substantial model-specific signal remains. These signals transfer across prompt sources and languages, with semantic representations proving most robust across languages. These findings show that model identity is recoverable at multiple resolutions, but that recoverability depends on model similarity and the evidence available in the text.

    PDF
  • arXiv cs.CLOct 20

    The Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned Counterparts

    Christophe Khalil, Aya Mourad

    We present our solution to the AKBC LM-KBC 2026 Shared Task, where we achieved a score of 0.6836 on the official leaderboard, more than double the baseline of 0.2964. This task requires generating all possible objects for subject-relation pairs using a language model with up to 32 billion parameters, with no retrieval or fine-tuning involved. We show that the prompting methodology is as important as the model architecture: while the instruction-tuned model version achieves 0.5681 with its chat interface, the base model achieves 0.6836 when prompted using text completion. Thus, instruction tuning decreases factual recall; we refer to this effect as the instruction tax, which is caused by the model's weights rather than the prompting method. Our final solution is fairly straightforward: we prompt the base model with some examples from the training data, generate 64--256 outputs, and retain only the repeated ones. Two specialized methods are then applied for each relation: one improves the recall of large answer sets, and the other verifies a person's vitality before predicting their place of death.

    PDF
  • arXiv cs.LGOct 20

    Relative Representations Enable Portable White-Box Monitoring Across Language Models

    Tim Bakker, Christos Louizos

    Independently trained autoregressive language models often acquire similar capabilities, but it remains unclear whether their internal representations organize behaviorally relevant information in compatible ways. We show that models do in fact organize information similarly by using specific behavioral probes that operate on compatible representations. This unlocks portable white-box monitoring: a probe developed and validated on one model can be reused when the model changes, without requiring labeled target data. To overcome incompatible native activation coordinates, we express each example through its angular distances to a shared set of anchors. We introduce a global anchored construction that summarizes information from all transformer layers and removes model-specific layer selection, so the same frozen probe can be straightforwardly applied to another model. We evaluate cross-model probe transfer across monitoring tasks on trivia datasets, safety monitoring, and mathematical reasoning. On average, transferred global anchored probes preserve at least 85% of same-model probe AUROC over chance. Anchored probes also support transfer to related datasets, remain robust across…

    PDF
  • arXiv cs.CLOct 20

    DeclineCraft: A RAG Abstention Benchmark for Jointly Measuring Combined Retrieval and Parametric Knowledge

    Atharva Thakur, Abulhair Saparov, Bruno Ribeiro

    Reliable retrieval-augmented generation (RAG) requires recognizing when neither retrieved documents nor parametric knowledge supports an answer. We introduce DeclineCraft, a dynamic abstention benchmark whose unanswerable questions target Minecraft feature additions after a corpus cut-off, with audits of possible parametric exposure. Later cut-offs support evaluation of future models. Across 27 LLMs, we measure Correct Abstention Rate (CAR; how often models acknowledge insufficient knowledge on unanswerable questions), Answerable Attempt Rate and Answer Accuracy. We find that (1) single-shot retrieval significantly raises CAR in 38 of 40 configurations (model and thinking setting) versus no retrieval. (2) Iterative RAG, in which the model self-assesses its context and can request up to two further retrieval rounds, significantly lowers CAR versus single-shot RAG in 30 of 40 configurations (mean 46.4%), with little change in Answer Accuracy (68.5% to 69.3%). Adding query rewriting and reranking to hybrid (dense & sparse) retrieval lowers CAR for all 12 models tested. (3) Larger models answer more accurately (Spearman $ρ= +0.60$ with total parameters), but neither model size nor…

    PDF
  • arXiv cs.CLOct 20

    Beyond a Single Sentiment Score: Topical and Affective Dimensions of Emoji Meaning on Twitter

    Rohan James, Ioannis Christofilogiannis, Yuuv Jauhari, Shreya Shah, Gauri Pethkar

    Emoji are widely treated as compact affective tokens whose meaning is summarised by a single sentiment score. We argue that this picture is incomplete. From a corpus of 16{,}575 English tweets and a per-emoji metric we call \emph{stability delta} (within-class minus between-class cosine similarity of sentence embeddings), we show that emojis used in tightly clustered topical contexts also exhibit \emph{more} polarised crowd-sourced sentiment, not less. Validated against the Kralj Novak et al.\ (2015) sentiment lexicon, the central correlation is Spearman $ρ= +0.361$ (Holm $p = 0.015$, 95\% bootstrap CI $[+0.10, +0.59]$); against the independent Ferré et al.\ (2025) Spanish 13-emotion ratings, $ρ= +0.509$ ($p = 0.0003$). The result survives permutation testing, BCa bootstrap, leave-one-out jackknife, partial correlation controlling for emoji frequency, and Holm correction across a four-test family. Topical coherence and affective dispersion are distinct dimensions of emoji meaning. As a downstream check we report leakage-free five-fold cross-validation results for sarcasm classification on the Emoji Sarcasm Dataset; all three baselines (a gated multimodal architecture, fine-tuned…

    PDF
  • arXiv cs.AIOct 20

    Is Sycophancy a Form of In-Context Updating?

    Itai Shapira, Myra Cheng, Hadas Orgad

    Factual sycophancy, a language model's deference to a user's false beliefs, is usually understood as a bid for the user's approval at the expense of truthfulness. We argue that this framing over-emphasizes the user and propose viewing sycophancy as a failure within the broader and generally useful process of in-context updating, by which models revise their answers based on information supplied during an interaction. We support this view with behavioral and mechanistic evidence. First, models' responses to user claims sit within a broader pattern of source-sensitive updating. They revise their answers in response to information attributed to external sources as well, more so when it appears better supported, and their deference to the user persists even when no user approval is at stake. Second, the internal components that support deference to the user are also causally important for in-context updating more broadly. Our results suggest that factual sycophancy arises when in-context updating gives a user's assertion excessive weight relative to its evidence. Because sycophancy is embedded in this process, reducing it risks reducing useful updating as well, a trade-off that calls…

    PDF
  • arXiv cs.CLOct 20

    From Abstraction to Action: DSLs for Natural Language Abstraction Interpretation and Execution

    Amit Lisha, Reut Tsarfaty

    Natural-language instructions often rely on high-level abstractions, such as asking an agent to ``stack blocks in a pyramid.'' Interpreting abstract instructions requires models to both identify the abstraction intended by the speaker, and unroll it into the many concrete actions that instantiate it. Language models struggle here: prior work has shown that performance degrades as the level of abstraction in the instruction rises. To bridge the gap between natural language abstraction and concrete actions, we propose to borrow from coding environments the notion of a {\em domain-specific language} (DSL), an explicit representation layer whose documented primitives name recurring abstractions that expand into concrete actions. We demonstrate the efficacy of DSLs for NL interpretation on \textsc{Hexagons}, a visually-grounded instruction-following task graded for abstraction. We further ask whether language models can induce such DSLs themselves from domain data. Our results show that while code generation consistently improves over direct inference, code generation over a human-curated DSL yields dramatic gains, up to 10 absolute F1 points, reaching the human skyline, with gains…

    PDF
  • arXiv cs.CLOct 20

    Forty Questions: Identifying a Language Model from One-Word Answers

    Tapan Parikh

    A model behind an API can be identified from its one-word answers to everyday questions such as "Name a sound" or "Name a poet". A model's profile records how often it gives each answer to each question. We attribute new answers to the model most likely to have given them. On a panel of 94 models, 40 answers identify the exact model 92.5% of the time, against 1.1% by chance. Profiles built through OpenRouter identified all ten models served by DeepInfra under blinded labels. A system prompt lowers accuracy by 6 to 16 points. We applied the method to 96 endpoints of 13 open models on OpenRouter, and 92 identify as the model they claim. Of the other four, one matches the claimed model with reasoning turned off. One serves Gemma 4 under the name Llama 4 Maverick: it names itself Gemma 4, and it is billed Gemma 4's token counts on every message. Two remain unresolved. Billing records also show context added to first-party models. Grok 4.7 is billed 1,247 input tokens for a one-line question that costs GPT-4o only 12 tokens, and five models state the current date without being billed for it. The questions come from a public census of model defaults, and the method costs cents per…

    PDF
  • arXiv cs.CLOct 20

    How Language Models Learn Taste: Brand Preference in LLMs

    Tapan Parikh

    Asked to name a running shoe brand, language models say Nike. Asked to recommend one, they say Brooks. This paper asks where models learn that taste. Across 102 models and 42 brand categories, the brand a model picks when recommending differs from the brand it names in 26. The field moves together to a shared recommendation. The Named brands are market leaders, and the Picked brands are mostly niche and specialist. Three open training pipelines show where this forms. Pretraining already attaches the recommended brand to advice. Supervised fine-tuning teaches the model to answer and mostly leaves the pick unchanged. Preference optimization (DPO) teaches the model which answer is better, and the pick moves in all three pipelines, by 11 to 24 points. The preference data contains almost no brands. DPO moves the model's judgments toward a second set of associations even when the preferred brand is not in the preference data, and the effect reaches beyond brands. Asked to choose a sauce, models switch from ketchup to pesto. We do not know exactly how these preferences arise. We suspect they come from the judge models that decide which answers count as better during preference training.…

    PDF
  • arXiv cs.CLOct 20

    Can Language Models Get "Aphasia" From Neuronal Ablation?

    Pratik Worah, Randall Bateman

    Progressive neuronal loss is the hallmark of neurodegenerative disease, yet how loss of neurons shapes the pattern of cognitive decline remains poorly understood. Here we systematically ablate neurons (computational units) in language models spanning recurrent long short-term memory (LSTM) and Transformer architectures and apply limited fine-tuning as a simple proxy for compensatory plasticity. With whole-unit ablation, LSTMs degrade gradually with syntactic and semantic faculties declining in parallel across mild-to-moderate damage. By contrast, Transformers exhibit late threshold-like collapse under feedforward multi-layer perceptron (MLP) ablation and smoother sigmoid-like decline under attention-head ablation. Qualitatively, MLP-ablated models continue to make within-category semantic substitutions (semantic paraphasias) alongside rising non-responses, paralleling Wernicke-type aphasia, while attention-head ablation produces a trend toward loss of semantic specificity similar to the semantic variant of primary progressive aphasia (svPPA). These findings indicate that feedforward and attentional pathways have functionally distinct failure modes, suggesting that…

    PDF
Load more
PDF