Knowledge catalogue
arXiv:2609.19366v1 Announce Type: new Abstract: Prior work has shown that internal harmfulness representations in large language models vary across risk categories, while sharing a common general harm
I'm trying to find out whether back-and-forth between two different LLMs improves task success beyond strong alternatives under a controlled resource budget — and I'd rather hear that it's already set
arXiv:2609.17804v1 Announce Type: new Abstract: Large language models solve grade-school math word problems with high accuracy, yet a single irrelevant clause inserted into the problem can collapse it
arXiv:2609.19144v1 Announce Type: cross Abstract: Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences because of their computational and me
arXiv:2609.18649v1 Announce Type: new Abstract: Warning: This paper contains examples of stereotypes and social bias. LLMs are increasingly used in interactive settings by the general public, making t
arXiv:2609.17981v1 Announce Type: cross Abstract: Speech Large Language Models (Speech-LLMs), typically built from a pre-trained speech encoder, a modality projector, and an LLM fine-tuned with Low-Ra
I'm at a crossroads with two grad school options that would take me in somewhat different research directions, and I wanted some general advice on these fields, their growth, and industry alignment. I
arXiv:2609.18598v1 Announce Type: cross Abstract: Self-driving laboratories can explore synthesis conditions autonomously, but their decision-making layer is typically a black-box optimizer, and the o
arXiv:2609.18148v1 Announce Type: new Abstract: The remarkable success of large language models (LLMs) has provided important inspiration for the next generation of recommender systems. Structurally,
arXiv:2609.19101v1 Announce Type: new Abstract: As models scale, reward hacking becomes more frequent, more sophisticated, and more consequential. Does it leave a telltale signature in model represent
arXiv:2609.16501v1 Announce Type: cross Abstract: De-identified resume screening assumes that redacting explicit fields prevents ethnocultural inference; however, recent audits attribute residual leak
arXiv:2609.16852v1 Announce Type: new Abstract: Industrial IoT environments increasingly deploy autonomous mobile robots for tasks such as material handling, product assembly, or infrastructure inspec
arXiv:2609.16517v1 Announce Type: cross Abstract: Resume screeners must infer job-relevant competence from resumes whose presentation can vary substantially in wording, structure, stylistic polish, an
arXiv:2609.16204v1 Announce Type: cross Abstract: Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and project
arXiv:2609.17475v1 Announce Type: new Abstract: Capable open-weight models make local coding and reasoning attractive, but their context and execution state strain laptop memory. We present JustFit, a
arXiv:2609.08797v2 Announce Type: replace-cross Abstract: The Potts model extends the Ising model to multinomial data. We introduce a Rater Ising-Potts model that uses agreement indicators between pai
arXiv:2609.13335v1 Announce Type: cross Abstract: Large Language Models (LLMs) have enabled more natural human-robot interaction, but open-source models often exhibit unstable long-horizon reasoning a
arXiv:2609.13580v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong capabilities across a wide range of natural language processing tasks. However, conventional fine-
arXiv:2609.15094v1 Announce Type: cross Abstract: In industrial recommendation feeds, presenting a static headline for an item often fails to satisfy the diverse, multimodal interests of the user popu
arXiv:2512.24565v4 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly serving as autonomous agents, and their utilization of external tools via the Model Context Protocol (
arXiv:2609.15838v1 Announce Type: cross Abstract: Per-matrix singular value decomposition (SVD) truncation is Eckart-Young optimal in the whitened Frobenius norm, but errors from independently compres
arXiv:2609.13152v1 Announce Type: new Abstract: Large language models (LLMs) perform strongly on static science benchmarks, yet their ability to reason about the physical world through active experime
arXiv:2609.14825v1 Announce Type: cross Abstract: Large language models (LLMs) are often deemed unsafe for clinical question answering because of their tendency to hallucinate. Retrieval augmentation,
arXiv:2609.13945v1 Announce Type: new Abstract: Natural-language descriptions of optimization problems may be incomplete or vague about numerical information that a solver requires, including costs, c
arXiv:2609.13582v1 Announce Type: cross Abstract: A clinical agent benchmark can report the same verdict on identical inputs while the agent files a materially different order on each run. Such agents
arXiv:2609.13205v1 Announce Type: cross Abstract: Sparse long-context inference requires efficient token retrieval in both prefill and decode. Existing methods often use different retrieval strategies
arXiv:2606.21869v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in multilingual settings, yet the energy costs of serving these models across different
arXiv:2609.13148v1 Announce Type: cross Abstract: Large language models are increasingly deployed as synthetic consumer panels, promising 97% cost reductions over traditional surveys. Yet aggregate va
arXiv:2609.12444v1 Announce Type: cross Abstract: Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the two
arXiv:2609.11995v1 Announce Type: new Abstract: Mobile sensing enables longitudinal monitoring of behavioral and physiological patterns in everyday settings. However, accurate prediction remains chall
arXiv:2609.12424v1 Announce Type: new Abstract: Reinforcement learning is now the standard way to train large language model agents on long-horizon tasks, where dozens of interdependent actions preced
arXiv:2609.13003v1 Announce Type: new Abstract: Binary-choice truth benchmarks ask models to choose between a correct and an incorrect answer, but if the two answers differ systematically in surface-l
arXiv:2609.12655v1 Announce Type: new Abstract: Large language model agents are expected to continuously adapt to new tasks and environments over their lifetime by reusing past experience. However, ex
arXiv:2609.11940v1 Announce Type: cross Abstract: The rapid diffusion of generative artificial intelligence raises privacy, latency, and performance concerns that motivate a shift toward 'local-first'
arXiv:2609.11028v1 Announce Type: cross Abstract: LM-agent benchmarks increasingly function as interactive evaluation infrastructure. Agents observe state, call tools, modify workspaces, submit artifa
arXiv:2609.10762v1 Announce Type: cross Abstract: Advances in large language models (LLMs) fuel the quest for scalable methods to assess the security of generated and security-sensitive software. Stat
arXiv:2607.18029v2 Announce Type: replace-cross Abstract: Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured qu
arXiv:2603.09309v3 Announce Type: replace Abstract: Verbalized confidence, in which LLMs report a numerical certainty score, is widely used to estimate uncertainty in black-box settings, yet the confi
arXiv:2609.11758v1 Announce Type: new Abstract: Allowing large language models (LLMs) to retrieve information from a set of trusted documents can increase reliability and reduce hallucination. However
arXiv:2509.18052v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to simulate human collective behavior, yet claims that such simulations are human-like remain lar
arXiv:2609.09794v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) on domain-specific data is essential for downstream adaptation. In many deployments, a participant cannot hold
arXiv:2604.01461v2 Announce Type: replace Abstract: Reducing hallucinations in Large Language Models (LLMs) is essential for accurate data extraction from large text corpora. Current methods, like pro
arXiv:2609.09349v1 Announce Type: new Abstract: Modern LLMs demonstrate impressive multilingual performance, yet standard benchmarks primarily reward selecting correct answers rather than evaluating g
arXiv:2609.09048v1 Announce Type: cross Abstract: Whether a language model looks demographically biased can depend on how the audit asks its question. A charitable-aid benchmark reports that the same
arXiv:2609.07568v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed for translation tasks, yet their implicit political positioning in such contexts remains unders
arXiv:2609.09887v1 Announce Type: new Abstract: LLMs have been used to simulate human decision-making in professional settings, yet their behaviors in common-law jury trials remain unexplored. We stud
arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explorat
arXiv:2602.18613v2 Announce Type: replace Abstract: Standard reranking evaluations study how a reranker orders candidates returned by an upstream retriever. This setup couples ranking behavior with re
Just a reminder for those out there itching to get into local llms - don't let FOMO or 'gear acquisition syndrom' take over. No matter the hobby, it's so easy to get stuck in a trap where we buy more
arXiv:2609.07288v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly employed to orchestrate robot behavior through natural-language interfaces, yet no benchmark exists to eva
arXiv:2609.06993v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly generate Markdown that is consumed by renderers, agents, code extractors, and structured downstream pipeline
arXiv:2508.19576v3 Announce Type: replace-cross Abstract: With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method - Group Relative Policy Optimi
arXiv:2609.05658v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being explored for automating SystemVerilog Assertion (SVA) generation, yet most evaluations report correc
arXiv:2609.07162v1 Announce Type: new Abstract: Several properties safety monitors are asked to certify, among them cross-tenant noninterference, sandbagging and evaluation awareness, are 2-safety hyp
arXiv:2609.08040v1 Announce Type: cross Abstract: The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies. Existing de
arXiv:2609.04738v1 Announce Type: new Abstract: In this paper, we study the problem of personalized survey response prediction using fine-tuned large language models (LLMs). This task poses unique cha
arXiv:2609.04444v1 Announce Type: new Abstract: Benchmarks for the side effects an agent causes on the way to a goal already exist, but HarvestBench is the first to put a price on avoiding the side ef
arXiv:2609.05036v1 Announce Type: new Abstract: AI alignment requires AI systems to adhere to human norms, values, or intentions. Under value pluralism there is no correct target, but a shared prerequ
arXiv:2609.04415v1 Announce Type: cross Abstract: Learning rich medical concept representations is essential for EHR prediction. Text-attributed knowledge graphs (TKGs) provide a natural foundation by
arXiv:2609.04198v1 Announce Type: new Abstract: Language-model judges now gate training data, score generations, and drive leaderboards. The judge is then a measurement instrument, resting on one rare