TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

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

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI
Fields · this week
All fields3082Multimodal501Agents478Frontier LLMs415Inference & serving250Image segmentation1683D scene149Graph learning142Learning verifiable rewards142Voice AI91Classifier & causal discovery82Forecasting time74Flow matching65Evals60Teacher policy distillation46Federated learning46All 32 fields

Open problems across fields

  • General in-context learning for embodied agents1 paper raises it · 0 address it

    Improving adaptability of models to new tasks and environments without task-specific fine-tuning is critical for scalable embodied intelligence.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Cost and latency in agentic systems2 papers raise it · 1 addresses it

    High computational and time costs limit practical deployment of agentic systems for real-world tasks.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
    • PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviewsraises · addresses
  • Physical-state verification and failure recovery1 paper raises it · 0 address it

    Robustness to irreversible failures and accurate state tracking are essential for reliable embodied control.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Evidence-grounded multimodal reasoning benchmarks1 paper raises it · 1 addresses it

    Current benchmarks often fail to ensure models use necessary audio-visual evidence, weakening evaluation reliability.

    • EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoningraises · addresses
  • Length generalization in sequential state tracking1 paper raises it · 1 addresses it

    Models struggle to maintain performance on problems much longer than their training data, limiting scalability.

    • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses

Named by an AI from these papers' abstracts.

Papers

  • arXiv cs.CLOct 16

    NLData2Opt: Benchmarking Parameter Derivation and Prediction for Modeling Optimization Problems from Natural Language and Data

    Lijia Liu, Kyohei Atarashi, Jiyi Li, Koh Takeuchi, Shunji Umetani +1

    Formulating optimization problems from raw inputs of problem descriptions and data is time-consuming and costly. While Large Language Models (LLMs) offer a promising way to automate this process, existing benchmarks overestimate their capabilities by relying on idealized inputs where all data is relevant and complete. This diverges from reality, where data-centric reasoning is required to extract, compute, and predict parameters from noisy sources. To address this, we introduce NLData2Opt, a benchmark to evaluate LLMs on the multi-stage reasoning inherent in practical optimization workflows. NLData2Opt decomposes problems into problem descriptions and data, and requires models to (1) extract relevant parameters from data containing misleading attributes, (2) compute missing parameters derived by transforming existing data attributes, and (3) predict unavailable future values from historical observations. Evaluation results show substantial performance decline relative to existing benchmarks, indicating that benchmark progress does not directly translate to formulation accuracy in practical optimization workflows. NLData2Opt is available at https://github.com/sumarivyn/NLData2Opt.

    PDF
  • arXiv cs.LGOct 16

    Batched Contextual Reinforcement II: Does RLVR Need Long Rollout Windows?

    Bangji Yang, Hongbo Ma, Ruihan Guo, Jiajun Fan, Xi Zhu +1

    Long rollout windows make reinforcement learning with verifiable rewards (RLVR) expensive, yet simply shortening them can remove the correctness signal: when every single-problem rollout truncates before an answer, group-relative accuracy advantages vanish. As a technical continuation of Batched Contextual Reinforcement (BCR), we study how concurrent rewards relax this dependence on long windows. Concurrent Constraint Reinforcement (CCR) places three independently verifiable problems in one capped training completion. Correct answers completed before truncation retain credit, while a shared budget encourages shorter useful reasoning without an explicit length penalty. We connect this mechanism to conditional reward- and update-variance analyses and study 4B and 8B mathematical reasoning models. Against single-problem GRPO with a 32k window, CCR with an 8,000-token window reduces tokens per training step from 975,464 to 174,957 on 4B and from 793,832 to 165,788 on 8B, saving 82.1% and 79.1%, respectively. An 8B training trace shows increasing accuracy reward alongside shorter completions. Single-problem evaluations provide supporting evidence of retained reasoning quality. These…

    PDF
  • arXiv cs.LGOct 16

    Learning to Be Guided: Shaping Latent Geometry for Classifier-Free Guidance

    Haoming Liu, Junhao Zhu, Shaoyi Zheng, Yuanhe Guo, Jinnuo Liu +2

    Classifier-free guidance (CFG) is a standard component of conditional diffusion models, and guided generation performance has become the \textit{de facto} measure of state-of-the-art models. Recent work on latent diffusion models seeks to learn latent spaces that are easier to model with diffusion. However, under CFG, generation additionally depends on how conditions are arranged in the latent space. We study this arrangement under discrete class conditions, termed \emph{class geometry}, and investigate what class geometry allows a latent space to work well with CFG. Under a Gaussian class model, we show that shifting variance from intra- to inter-class at fixed total variance makes classes more distinguishable under noise, and derive a noisy posterior objective whose per-sample descent direction is proportional to the oracle CFG correction. Based on the analysis, we propose Prototype Regularization (PR), a lightweight surrogate for the intractable noisy posterior objective, which applies a cosine prototype classifier to spatially pooled latents. With a controlled training budget (20 epochs for VAE, 80 epochs for DiT), adding PR to an LDM baseline reduces guided gFID on ImageNet…

    PDF
  • arXiv cs.AIOct 16

    ToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning

    Sicong Li, Qianqian Xu, Zhiyong Yang, Zitai Wang, Longtao Huang +2

    Parameter-Efficient Fine-Tuning (PEFT) has emerged as a prevalent strategy for adapting large pre-trained models. Among PEFT techniques, reparameterization-based methods, particularly those that employ low-rank or sparsity structures, have attracted significant attention. However, these approaches often underperform full fine-tuning. Specifically, low-rank methods constrain the update rank, which is misaligned with the inherently high-rank nature of full fine-tuning. In contrast, sparsity-based techniques limit the flexibility of the parameter space and compromise connectivity across weights. To overcome these limitations, we explore the use of Toeplitz matrices, whose entries are constant along each diagonal, therefore providing a compact parameterization without imposing explicit rank or sparsity constraints. A straightforward approach is to update weights via a product of Toeplitz matrices. However, similar to RNNs, long multiplicative chains often lead to gradient instability. To address this issue, we propose \textbf{ToPA}, a more refined version of this idea that replaces standard Toeplitz matrices with block-wise Toeplitz, greatly increasing each factor's capacity and…

    PDF
  • arXiv cs.GTOct 16

    Cooperation Without Adaptation: LLM Agents in a Collective-Risk Dilemma

    Trung-Kiet Huynh, Dao-Sy Duy-Minh, Chi-Nguyen Tran, Phu-Hoa Pham, Phu-Quy Nguyen-Lam +2

    Language-model agents are increasingly deployed to act on behalf of people in settings where individual decisions shape shared outcomes. We examine whether five production models adapt their contributions to changing risks and partner behaviour, or instead follow a relatively fixed strategy. In a collective-risk dilemma game (CRG), six players contribute to a shared pool over ten rounds; if the pool falls short of its target, a catastrophe may destroy their remaining resources. Four models contributed approximately an equal share at every positive risk level, and four of the five also contributed when risk was zero, even though contributing could not improve their payoff. Explicitly stating that only the agent's own payoff mattered reduced zero-risk contributions for most models, while a more neutral prompt did not. Several models correctly identified which action offered the higher expected payoff at different risk levels, yet their contributions changed little. Against fixed partners, no model consistently chose the payoff-maximising response, and in mixed-model groups, a single agent's shortfall in the final round could cause an otherwise successful group to fail. Payoff-based…

    PDF
  • arXiv cs.SEOct 16

    No One-Size-Fits-All: Adaptive Code Editing with Feature-Based Strategy Selection

    Jun Wan, Zhongxin Liu, Dajun Chen, Wei Jiang, Yong Li +1

    Large language models have shown strong potential in automating code editing (CE) tasks, yet most existing systems rely on a fixed CE strategy (i.e., one-step, search-replace, and plan-apply) across diverse scenarios. In practice, CE tasks vary widely in code context, edit locality, and semantic complexity, causing no single strategy to perform consistently well. Moreover, systematic studies on the relationship between strategies and CE tasks remain scarce, limiting further optimization of LLM-based code editing strategies. To address this gap, we construct CEBench, comprising 500 real-world CE tasks curated from SWE-bench. Then we compare three representative CE strategies (one-step, search-replace, plan-apply). Our study reveals two key findings: (1) each strategy exhibits distinct advantages for specific CE tasks, with no universal optimality; (2) strategy effectiveness is significantly influenced by four core task features: total lines of code, modification type, modification scope, and task type. Motivated by these findings, we propose Ace, an adaptive code editing framework that dynamically selects optimal CE strategies based on task features. Unlike classifier-based or…

    PDF
  • arXiv cs.CLOct 16

    Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data

    Zesheng Shi, Xue Li, Chenrui Dai, Jing Li

    LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate directives with adversarial prompt injections, and the model must follow the former while rejecting the latter. Existing defenses suppress or trust all external instructions, collapsing the safety-utility frontier and forcing a choice between over-refusal and over-compliance. We argue the missing capability is \textbf{per-instruction credit attribution} and formalize it as External-Data Instruction Classification, an identify-classify-act decision over each embedded directive. We propose \textbf{EDIC}, a decomposed reward framework for per-instruction compliance. A scene-grounded pipeline injects mixed beneficial and harmful instructions with counterfactual filtering, while a generative judge is initialized by SFT and refined with GRPO to attribute compliance at the instruction level. The judge then produces a reward that separately encourages beneficial compliance and penalizes harmful compliance for RL training. Across two backbones and five benchmarks, EDIC improves both safety and utility over the strongest prior defense, lifting harmful-rejection by up to…

    PDF
  • arXiv eess.IVOct 16

    ProtoGTX: Prototype-Aligned Graph Transformer for Explainable Whole-Slide Image Analysis

    Iori Azuma, Hiroyuki Kusuhara, Tadahaya Mizuno

    Deep learning has achieved strong performance in computational pathology, but explaining whole-slide image (WSI) predictions remains challenging. Existing explanation methods often highlight important regions without identifying their morphological patterns, leaving a gap between patch-level computational evidence and slide-level pathological interpretation. We propose ProtoGTX, a graph-based framework that combines spatial contextualization with a flexible morphological prototype vocabulary. ProtoGTX separates the reference prototypes used to define morphological concepts from the predictive model: the reference vocabulary can be generated from training data by unsupervised clustering or supplied externally, and remains fixed during classifier training. Patch features are first contextualized over a spatial graph, after which learnable prototypes representing morphological concepts are optimized through cross-attention. Their slide-level activation profile is aligned with the morphological composition induced by the fixed reference prototype bank. On the CPTAC and BRACS datasets, ProtoGTX outperforms the evaluated MIL, prototype-based, and graph-based baselines, with…

    PDF
  • arXiv cs.AIOct 16

    Look Back, Correct Forward: Error Feedback Calibration for Time Series Forecasting

    Haonan Yang, Yulin He, Zhuo Li

    Time series forecasting models are increasingly deployed in continuously evolving environments. After a forecast is issued, future observations gradually arrive and reveal how the model has failed. Existing methods mainly treat such observations as supervision for parameter updates. However, it remains unclear whether verified forecasting errors can themselves provide causal feedback for correcting future predictions. To address this, we introduce Error Feedback Calibration (EFC), a fully test-time framework for deterministic post-hoc correction of time series forecasting. EFC constructs a Causal Error Diagonal (CED) from revealed errors of overlapping historical forecasts, providing a fresh view of the frozen forecaster's recent failure behavior. Then Cumulative Error Transport (CET) maps this error state to future residuals using cumulative estimation, while temporal out-of-sample validation controls the correction strength. Temporal Residual Learning (TRL) further predicts only the residual structure left after CET from recent CED trajectories, rather than relearning the entire forecasting error. Extensive experiments across forecasting backbones and datasets show that EFC…

    PDF
  • arXiv cs.AIOct 16

    ShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers

    Kun Zhai, Teng Li, Yunhao Feng, Xingjun Ma

    Federated Prompt Tuning (FPT) adapts large vision--language models by freezing the pretrained backbone and optimizing only lightweight prompt parameters across clients. Although this design improves communication and parameter efficiency, it creates an overlooked security risk. Since the backbone is shared and frozen, a malicious client can induce backdoor behavior through the representation space while keeping its uploaded prompt updates close to benign ones. We propose \textbf{ShadowFPT}, a targeted backdoor attack that exploits this frozen-backbone attack surface. ShadowFPT first pretrains a learnable \emph{Shadow Trigger} against the frozen CLIP visual encoder, using either auxiliary public data or the malicious client's local data, so that triggered inputs are steered toward the target class in representation space. During federated prompt tuning, the malicious client adapts the trigger under the current global prompt and then optimizes its local prompt on both clean and triggered samples. Only prompt parameters are uploaded to the server, while the trigger and frozen encoders remain local. By shifting most of the attack burden from prompt updates to trigger-induced…

    PDF
  • arXiv cs.AIOct 16

    MS-Eval: Benchmarking Sub-Agent Delegation and Orchestration in MCP-Intensive Working Scenarios

    Bowen Ding, Qixin Wang, Lexing Ruan, Weiyi Lu, Qiwei Ge +2

    LLM agents are increasingly integrated into real-world works, yet they must handle diverse domain-specific tools and complex multi-sub-task problems that sequential tool invocation resolves inefficiently and with severe context bloat. The Main-Agent Delegation and Sub-Agent Execution (MAD-SAE) paradigm addresses these issues by delegating sub-tasks to specialized sub-agents for parallel execution in isolated contexts, but its delegation and orchestration quality remains unquantified. We introduce MS-Eval, a unified evaluation kit comprising an MCP-intensive benchmark, a controlled execution harness, tailored delegation and orchestration metrics, and the MSQ index for comprehensive assessment. Evaluating four MAD-SAE variants and eight frontier models reveals that (1) sub-agent specialization (Spec) is the best practical practice; (2) open-source models are largely competitive with few exceptions; and (3) MAD-SAE generally raises cost with contingent payoff, benefiting most open-source models in both performance and efficiency while leaving closed-source models with higher cost and degraded performance. Our case study further traces these gains to better single-agent solutions,…

    PDF
  • arXiv cs.AIOct 16

    Evo-B&B: Behavior-Aware LLM-Guided Joint Evolution of Branching and Node Selection Policies for MILP

    Jiayu Chen, Chentong Chen, Yuhan Liu, Ye Fan, Jianyong Sun +1

    In branch-and-bound for Mixed-Integer Linear Programming (MILP), branching and node selection are two critical and tightly coupled decisions, yet most existing learning-based approaches focus on optimizing them separately. We propose Evo-B&B, an LLM-guided evolutionary framework that jointly evolves executable branching and node selection policies using end-to-end SCIP solving feedback. To improve search efficiency and reduce redundant evaluations of behaviorally similar policies, Evo-B&B introduces a behavior-aware multi-island evolutionary mechanism. It measures policy similarity from branching and node-selection behaviors on a fixed set of B&B decision states and uses this similarity to preserve population diversity. We evaluate Evo-B&B on four standard MILP benchmarks across multiple instance scales. Experimental results show that Evo-B&B achieves competitive solving performance and generalizes well to larger-scale instances, while ablation studies further demonstrate the effectiveness of joint evolution and behavior-aware diversity management.

    PDF
  • arXiv cs.CLOct 16

    Uncertainty-Aware Budget Allocation for Efficient LLM Tree Search

    Jianguo Huang, Zhiyi Lyu, Fuxiang Zhang, Yanchen Deng, Deheng Ye +1

    Tree search enhances multi-step reasoning in large language models (LLMs), yet prevailing methods expand every step with a fixed budget, irrespective of the marginal utility of expansion. We first show, across existing search algorithms, that continuations sampled from a shared intermediate state are largely duplicates and collapse to a few distinct answers. Critically, we find that the semantic dispersion of sibling actions predicts the redundancy of their downstream continuations, permitting a subtree's budget to be fixed before expansion. An information-theoretic analysis motivates this: treating the per-step budget as the Monte Carlo sample size for estimating a step's residual answer entropy, we derive a sufficient budget that shrinks with sibling dispersion. We accordingly propose $\textbf{Uncertainty-Aware Allocation}$ (UAA), a training-free framework that decouples value from uncertainty: values determine which candidates are promising, while uncertainty, estimated from sibling dispersion at no additional model cost, determines how many merit expansion, via uncertainty-aware pruning and uncertainty-aware budgeting. Across mathematical reasoning, logical reasoning, and…

    PDF
  • arXiv cs.ROOct 16

    Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors

    Carl Qi, Weijun Dong, Xiaojie Wang, Peiyi Chen, Rahul Sajnani +6

    Generalist robot policies offer strong behavioral priors, but achieving deployment-level reliability and throughput remains difficult. Reinforcement learning (RL) can improve these policies, yet its effectiveness is constrained by the cost of online interaction. Existing methods adapt frozen flow-matching policies by treating noise space as a continuous action space. We show that this behaviorally unstructured space makes exploration inefficient, often preventing these methods from extracting meaningful learning signals on challenging tasks. We introduce AnchorQ, which enables coarse-to-fine policy improvement through a structured, refinable latent action representation. At each decision step, AnchorQ uses flow reversal to map reference behaviors to state-conditioned latent anchors, samples local particles around those anchors, and applies value-guided sampling to explore promising refinements. Our analysis shows that anchors reduce identification complexity at the cost of support bias; particle refinement trades this bias against action-class complexity; and critic accuracy determines the reliability of KL-regularized, value-guided selection. Across simulated and real-world…

    PDF
  • arXiv eess.IVOct 16

    Measurement-Adaptive Light-Cone Transform for Robust Non-Line-of-Sight Imaging

    Lianfang Wang, Xueying Liu, Junnan Dong, Qinghua Zhang, Jun Liu +2

    Practical non-line-of-sight (NLOS) measurements are affected by noise and deviations from idealized light transport, which can degrade reconstruction with conventional light-cone transform (LCT) methods. We propose the Measurement-Adaptive Light-Cone Transform (MALCT), a physics-guided framework that retains the efficient Fourier-domain inversion structure of LCT. {Within a unified variational formulation, MALCT combines the analytical response with a shared learned response through measurement-conditioned weighting and predicts a measurement-conditioned, frequency-dependent regularization map.} An attention-enhanced spatio-temporal feature extraction module captures long-range temporal dependencies and local spatial correlations to support reconstruction under low-signal conditions. Experiments on synthetic data and real measurements from different NLOS systems demonstrate improved reconstruction quality. Controlled evaluations further assess robustness to temporal-response broadening and reduced acquisition time. MALCT also preserves scene structures with spatial sampling grids down to $32\times32$, supporting its potential for NLOS imaging under limited acquisition budgets.

    PDF
  • arXiv cs.LGOct 16

    Benchmarking and Enhancing Agentic Causal Discovery

    Pingchuan Ma, Rui Ding, Shuai Wang

    LLM agents can now run causal discovery algorithms on a dataset and report what comes out. Whether they do more than that, such as noticing where an algorithm went wrong and fixing it with further tests, is hard to tell from current benchmarks. Most of them give the variables meaningful names, and an LLM shown only the names of the Tübingen cause-effect pairs already gets 99% of the directions right. With the names removed, the data are usually clean enough that picking a better algorithm than PC closes most of the gap. We introduce Heuresis, a benchmark of anonymous simulated datasets whose mechanisms range from linear Gaussian to heavy-tailed. For each family of datasets it separates what a better existing algorithm can gain from what only a closer look at the data can gain, and it traces every edge an agent changes. Every family leaves a gap that none of the algorithms, the router and the two causal-discovery foundation models we ran can close, so a score above the best chosen algorithm has to come from using the data. We instantiate the benchmark with an agent harness and three LLMs, GPT-6.1 Sol, Claude Opus 5.5 and Qwen 3.8 Flash. GPT-6.1 Sol surpasses the best chosen…

    PDF
  • arXiv eess.IVOct 16

    DinoMUSE: A DINOv2-guided Framework for Unsupervised Lateral Motion Estimation in Ultrasound Elastography

    Xiyao Meng, Xingyue Wei, Baihua Luo, Bo Peng, Jianwen Luo

    Quasi-static ultrasound elastography (USE) is a non-invasive imaging method for assessing soft tissue mechanical properties. Limited by low resolution, low sampling frequency and lack of phase information in the lateral direction, accurate lateral motion estimation remains a critical bottleneck in USE. Existing methods mainly rely on local image matching and physical constraints (such as tissue incompressibility assumption and effective Poisson's ratio), which lack sufficient contextual information. We present DinoMUSE, a DINO-guided mixture-of-experts (MoE) framework for unsupervised lateral motion estimation in USE. DinoMUSE incorporates high-level visual representations learned by DINOv2 into the motion estimation network to provide global contextual guidance. To facilitate effective interaction between DINOv2 features and local matching features, an MoE-based feature-fusion module adaptively transforms and integrates the two representations. Evaluations against NCC, GLUE, RAFT, and sPICTURE on simulation and in-vivo breast datasets show that DinoMUSE substantially improves lateral estimation accuracy while maintaining competitive axial performance. Specifically, DinoMUSE…

    PDF
  • arXiv cs.CVOct 16

    Variational and Decomposed method for Mitigating Bimodal Bias in Robust Visual Question Answering

    Yihan Zhao, Yuncheng Jiang

    Visual question answering (VQA) models are known to suffer from the bias issue, which refers to overfitting the regularities of frequent patterns. Previously, researchers only consider the language bias. Recently, the multimodal bias is noticed. However, what multimodal bias is remains unclear. In this paper, we investigate the multimodal bias in counting and non-counting questions. We find that they have distinct underlying mechanism, so their biases come from distinct reasons. We provide valuable interpretations of VQA counting mechanism: \textbf{quantity information stems from the magnitude of the multimodal features in specific dimensions.} Thus, counting bias stems from the vision side and propagates to multimodal features through modality fusion, while the non-counting bias stems from primarily language bias and slightly vision bias. Thus, we propose a method to deal with them differently: Variational and Decomposed method for mitigating Bimodal Bias (VDB). It extracts bimodal bias affected by different proportion of vision and language sides. We introduce variational bias models utilizing the principle of Variational Auto-Encoder to learn mainly language bias with slight…

    PDF
  • arXiv cs.CVOct 16

    VTrajEmbed: Aligning Text with Video Object Trajectories via Spatiotemporal Embeddings

    Ruizhi Chen, Zining Fan, Yudi Guo, Jiang Liu, Zhiyu Lin +3

    Fine-grained alignment between text and video object trajectories is a core challenge in multimodal understanding. Existing embedding models excel at global retrieval, yet their single global representation entangles multiple objects and their spatiotemporal dynamics, limiting direct object-level grounding. To address this issue, we propose VTrajEmbed, an embedding model that decomposes a video into object trajectories and aligns each trajectory embedding with text for object-level grounding through retrieval. Our main contributions: (1)Slow-Fast Trajectory Encoding, a dual-branch architecture that establishes trajectory representations by densely sampling low-resolution frames for high-frequency motion cues and sparsely selecting high-resolution frames for scene context, aggregated by a shared LLM backbone; (2)Mask-Guided Contrastive Learning, a training objective built upon these representations that couples an intra-group loss and a batch-level bidirectional loss under a relation mask, excluding unverified relations and preventing confirmed matches from becoming false negatives; (3)Text2Traj-Bench, a trajectory-level text-video benchmark with model-assisted construction and…

    PDF
  • arXiv cs.CLOct 16

    The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level Falls

    Lucas Resck, Jingyi Sun, Qianli Wang, Isabelle Augenstein, Anna Korhonen

    Chain-of-Thought (CoT) faithfulness matters for monitoring, explaining and safely deploying large language models, yet it has been studied mostly in English. Languages differ in level, the amount of text available to learn from, so models know less in lower-resource languages, which may change how much they rely on their reasoning. To our knowledge, we are the first to relate CoT faithfulness to both resource level and task type (knowledge- or reasoning-intensive). On parallel multiple-choice questions from Multilingual Massive Multitask Language Understanding (MMMLU) in eight languages, faithfulness rises as resource level falls on knowledge-intensive tasks but not on reasoning-intensive ones, a gap that points the same way across four models and several faithfulness measures. We propose, and find support for, the Reliance Hypothesis: models rely more on their reasoning when they cannot recall the answer, as in lower-resource languages on knowledge-intensive tasks. Model confidence partly explains the effect of resource level, but not the knowledge-reasoning gap. Languages in which models are less confident rely more on reasoning, yet less confident answers within a language do…

    PDF
Load more

Rising research topics

  • Training & fine-tuning42+90.9%
  • AI safety29+61.1%
  • Computer vision29+31.8%
  • Evals60+25.0%
  • Federated learning46+21.1%
  • Code models13+18.2%
  • Quantum machine learning24+14.3%
  • Image & video generation20+5.3%