This study presents an LLM-assisted annotation pipeline for the sociolinguistic and topical analysis of bilingual discourse in two typologically distinct contexts: Spanish-English and Spanish-Guaraní. Using large language models, we automatically labeled topic, genre, and discourse-pragmatic functions across a total of 3,691 code-switched sentences, integrated demographic metadata from the Miami Bilingual Corpus, and enriched the Spanish-Guaraní dataset with new topic annotations. The resulting distributions reveal systematic links between gender, language dominance, and discourse function in the Miami data, and a clear diglossic division between formal Guaraní and informal Spanish in Paraguayan texts. These findings replicate and extend earlier interactional and sociolinguistic observations with corpus-scale quantitative evidence. The study demonstrates that large language models can reliably recover interpretable sociolinguistic patterns traditionally accessible only through manual annotation, advancing computational methods for cross-linguistic and low-resource bilingual research.

Memory and computation remain core bottlenecks in long-horizon LLM inference due to the quadratic cost of self-attention and the ever-growing key-value (KV) cache. Existing strategies for memory-bounded inference, such as quantization, offloading, or heuristic KV eviction, either incur high orchestration costs or rely on unreliable attention-based proxies of importance. We propose TRIM-KV, a novel approach that learns each token's intrinsic importance at creation time via a lightweight retention gate. Each gate predicts a scalar retention score that decays over time, reflecting the long-term utility of the token for a specific layer and head. Tokens with low scores are evicted when the memory budget is exceeded, ensuring that the cache always contains the most critical tokens. TRIM-KV is trained efficiently through distillation from a frozen LLM combined with a capacity loss, requiring only gate fine-tuning and adding negligible inference overhead. Across mathematical reasoning (GSM8K, MATH-500, AIME24), procedural generation (LongProc), conversational long-memory benchmarks (LongMemEval), and long-context understanding (LongBench and SCBench), TRIM-KV consistently outperforms strong eviction and learnable retrieval baselines, especially in low-memory regimes. Remarkably, it even surpasses full-cache models in some settings, showing that selective retention can serve as a form of regularization, suppressing noise from uninformative tokens. Qualitative analyses further reveal that learned retention scores align with human intuition, naturally recovering heuristics such as sink tokens, sliding windows, and gist compression without explicit design. Beyond efficiency, retention scores provide insights into layer- and head-specific roles, suggesting a new path toward LLM interpretability.

Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.

The current literature on memorization in Natural Language Models, especially Large Language Models (LLMs), poses severe security and privacy risks, as models tend to memorize personally identifying information (PIIs) from training data. We introduce Randomized Masked Fine-Tuning (RMFT), a novel privacy-preserving fine-tuning technique that reduces PII memorization while minimizing performance impact. Using the Enron Email Dataset, we demonstrate that RMFT achieves an 80.81% reduction in Total Extraction Rate and 80.17% reduction in Seen Extraction Rate compared to baseline fine-tuning, outperforming deduplication methods while maintaining only a 5.73% increase in perplexity. We present MaxTER, a Pareto-optimal evaluation framework for assessing privacy-utility tradeoffs, and show the performance of RMFT vs Deduplication by Area Under The Response Curve (AURC) metric.

Training vision language models (VLMs) aims to align visual representations from a vision encoder with the textual representations of a pretrained large language model (LLM). However, many VLMs exhibit reduced factual recall performance compared to their LLM backbones, raising the question of how effective multimodal fine-tuning is at extending existing mechanisms within the LLM to visual inputs. We argue that factual recall based on visual inputs requires VLMs to solve a two-hop problem: (1) forming entity representations from visual inputs, and (2) recalling associated factual knowledge based on these entity representations. By benchmarking 14 VLMs with various architectures (LLaVA, Native, Cross-Attention), sizes (7B-124B parameters), and training setups on factual recall tasks against their original LLM backbone models, we find that 11 of 14 models exhibit factual recall degradation. We select three models with high and two models with low performance degradation, and use attribution patching, activation patching, and probing to show that degraded VLMs struggle to use the existing factual recall circuit of their LLM backbone, because they resolve the first hop too late in the computation. In contrast, high-performing VLMs resolve entity representations early enough to reuse the existing factual recall mechanism. Finally, we demonstrate two methods to recover performance: patching entity representations from the LLM backbone into the VLM, and prompting with chain-of-thought reasoning. Our results highlight that the speed of early entity resolution critically determines how effective VLMs are in using preexisting LLM mechanisms. More broadly, our work illustrates how mechanistic analysis can explain and unveil systematic failures in multimodal alignment.

Large Reasoning Models (LRMs) achieve strong performance on complex reasoning tasks by generating long Chains of Thought (CoTs). However, this paradigm might incur substantial token overhead, especially when models "overthink" by producing lengthy reasoning chains, which can even lead to incorrect answers. A promising direction is the symbolic-solver-integrated approach, which leverages the code generation capabilities of LLMs to translate reasoning tasks into executable code and then solve them with a symbolic solver. In this paper, we explore an open question of when the conventional long-CoT can be enhanced by symbolic solvers. Our experimental results show that the symbolic-solver-integrated method only helps when the problem requires limited implicit reasoning but involves an ample search space. The latest LLMs, like GPT-4o, show better performance on deductive problems with shallow reasoning depth, while the symbolic-solver-integrated method significantly improves the LLMs' performance in constraint satisfaction problems that require repeated backtracks. When a declarative exemplar is provided, even CodeLlama-13B can outperform GPT-4o in difficult Zebra puzzles.

Vibe coding is a new programming paradigm in which human engineers instruct large language model (LLM) agents to complete complex coding tasks with little supervision. Although it is increasingly adopted, are vibe coding outputs really safe to deploy in production? To answer this question, we propose SU S VI B E S, a benchmark consisting of 200 feature-request software engineering tasks from real-world open-source projects, which, when given to human programmers, led to vulnerable implementations. We evaluate multiple widely used coding agents with frontier models on this benchmark. Disturbingly, all agents perform poorly in terms of software security. Although 61% of the solutions from SWE-Agent with Claude 4 Sonnet are functionally correct, only 10.5% are secure. Further experiments demonstrate that preliminary security strategies, such as augmenting the feature request with vulnerability hints, cannot mitigate these security issues. Our findings raise serious concerns about the widespread adoption of vibe-coding, particularly in security-sensitive applications.

Process reward models (PRMs) that provide dense, step-level feedback have shown promise for reinforcement learning, yet their adoption remains limited by the need for expensive step-level annotations or ground truth references. In the second stage, we use these verification outputs as synthetic training data to fine-tune generative process reward models, which subsequently serve as reward signals during training. We show that aggregating multiple independent verifications at the step level produces training data for process reward models that surpass ground-truth outcome supervision--achieving 67.5 F1 on ProcessBench (a benchmark for identifying erroneous steps in mathematical reasoning) compared to 66.4 for reference-guided training and 61.9 for GPT -4o. In the final stage, we apply our generative PRM with chain-of-thought verification (PRM-CoT) as the reward model in RL experiments on mathematical reasoning, and introduce format constraints to prevent reward hacking. Our work enables reference-free RL training that exceeds ground-truth methods, opening new possibilities for domains lacking verifiable answers or accessible ground truth. Large language models (LLMs) have demonstrated impressive capabilities across diverse tasks, from achieving gold-medal performance at the International Mathematical Olympiad to autonomous agentic coding (Castelvecchi, 2025; Luong & Lockhart, 2025; Y ang et al., 2024b; Hurst et al., 2024; Anthropic, 2025). Recent breakthroughs like OpenAI's o1 and DeepSeek's R1 demonstrate that reinforcement learning (RL) post-training can significantly enhance reasoning capabilities beyond supervised fine-tuning alone (Jaech et al., 2024; Guo et al., 2025), as RL enables models to explore diverse solution paths and learn from feedback rather than imitation (Chu et al., 2025). While RL post-training shows promise, current approaches rely on verifiers that require ground truth references. Traditional methods rely on either discriminative verifiers that provide binary correctness signals (Cobbe et al., 2021) or rule-based verifiers using exact answer matching (RL VR) (Guo et al., 2025; Hu et al., 2025), both offering only sparse, outcome-level rewards. Recent advances introduce Process Reward Models (PRMs) that provide denser, step-level feedback to improve training stability and credit assignment (Lightman et al., 2023; Wang et al., 2024; Uesato et al., 2022), including co-evolving approaches like T ANGO (Zha et al., 2025) and PRIME (Y uan et al., 2024) that jointly train the verifier alongside the policy model. Work done while as an intern at Amazon AGI. Stage III: Apply trained PRMs in RL with GRPO using different reward designs. PRIME requires outcome-level correctness labels to train its PRM (Zha et al., 2025; Y uan et al., 2024).

Causal attributions are claims that link an outcome to a cause (Kirfel et al., 2022). Causality is so embedded in human reasoning that causal attributions have been shown to emerge immediately in times of crisis (Graham and Singh, 2024), as well as offered spontaneously when people are asked to think about political issues (Iyengar, 1987). Furthermore, because causal attributions are relational, rather than treating actors and events as isolated, they highlight the underlying relational reasoning people use to connect events, assign responsibility, and justify actions (V ossing, 2023). Framing is fundamentally a process of making causal explanations, or communicating causal attributions: "[Frames] define problems-determine what a causal agent is doing with what costs and benefits, usually measured in terms of common cultural values; diagnose causes-identify the forces creating the problem; make moral judgments-evaluate causal agents and their effects; and suggest remedies-offer and justify treatments for the problems and predict their likely effects."(Entman,

Large Language Models (LLMs) have revolutionized the ability to understand and generate text, enabling significant progress in automatic knowledge graph construction from text (Text2KG). Many Text2KG methods, however, rely on iterative LLM prompting, making them computationally expensive and prone to overlooking complex relations distributed throughout the text. To address these limitations, we propose InvertiTune, a framework that combines a controlled data generation pipeline with supervised fine-tuning (SFT). Within this framework, the data-generation pipeline systematically extracts subgraphs from large knowledge bases, applies noise filtering, and leverages LLMs to generate corresponding natural text descriptions, a task more aligned with LLM capabilities than direct KG generation from text. This pipeline enables generating datasets composed of longer texts paired with larger KGs that better reflect real-world scenarios compared to existing benchmarks, thus supporting effective SFT of lightweight models for single-shot KG construction. Experimental results on CE12k, a dataset generated using the introduced pipeline, show that InvertiTune outperforms larger non-fine-tuned LLMs as well as state-of-the-art Text2KG approaches, while also demonstrating stronger cross-dataset generalization on CrossEval-1200, a test set created from three established benchmark datasets and CE12k. These findings highlight the importance of realistic, high-quality training data for advancing efficient and high-performing Text2KG systems.