Large Language Models (LLMs) exhibit strong reasoning capabilities in complex tasks. However, they still struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA). We attribute this to the semantic gap between structured knowledge graphs (KGs) and unstructured queries, caused by inherent differences in their focuses and structures. Existing methods usually employ resource-intensive, non-scalable workflows reasoning on vanilla KGs, but overlook this gap. To address this challenge, we propose a flexible framework, Enrich-on-Graph (EoG), which leverages LLMs' prior knowledge to enrich KGs, bridge the semantic gap between graphs and queries. EoG enables efficient evidence extraction from KGs for precise and robust reasoning, while ensuring low computational costs, scalability, and adaptability across different methods. Furthermore, we propose three graph quality evaluation metrics to analyze query-graph alignment in KGQA task, supported by theoretical validation of our optimization objectives. Extensive experiments on two KGQA benchmark datasets indicate that EoG can effectively generate high-quality KGs and achieve the state-of-the-art performance. Our code and data are available at https://github.com/zjukg/Enrich-on-Graph.

Steven Adler used to lead product safety at OpenAI. On this week's episode of, he talks about what AI users should know about their bots. When the history of AI is written, Steven Adler may just end up being its Paul Revere--or at least, one of them--when it comes to safety. Last month Adler, who spent four years in various safety roles at OpenAI, wrote a piece for The New York Times with a rather alarming title: "I Led Product Safety at OpenAI. In it, he laid out the problems OpenAI faced when it came to allowing users to have erotic conversations with chatbots while also protecting them from any impacts those interactions could have on their mental health. "Nobody wanted to be the morality police, but we lacked ways to measure and manage erotic usage carefully," he wrote. "We decided AI-powered erotica would have to wait." Adler wrote his op-ed because OpenAI CEO Sam Altman had recently announced that the company would soon allow " erotica for verified adults ."

Computational notebooks have become popular for Exploratory Data Analysis (EDA), augmented by LLM-based code generation and result interpretation. Effective LLM assistance hinges on selecting informative context -- the minimal set of cells whose code, data, or outputs suffice to answer a prompt. As notebooks grow long and messy, users can lose track of the mental model of their analysis. They thus fail to curate appropriate contexts for LLM tasks, causing frustration and tedious prompt engineering. We conducted a formative study (n=6) that surfaced challenges in LLM context selection and mental model maintenance. Therefore, we introduce NoteEx, a JupyterLab extension that provides a semantic visualization of the EDA workflow, allowing analysts to externalize their mental model, specify analysis dependencies, and enable interactive selection of task-relevant contexts for LLMs. A user study (n=12) against a baseline shows that NoteEx improved mental model retention and context selection, leading to more accurate and relevant LLM responses.

Background: Large Language Models emerged with the potential of provoking a revolution in software development (e.g., automating processes, workforce transformation). Although studies have started to investigate the perceived impact of LLMs for software development, there is a need for empirical studies to comprehend how to balance forward and backward effects of using LLMs. Objective: We investigated how LLMs impact software development and how to manage the impact from a software developer's perspective. Method: We conducted 22 interviews with software practitioners across 3 rounds of data collection and analysis, between October (2024) and September (2025). We employed socio-technical grounded theory (STGT) for data analysis to rigorously analyse interview participants' responses. Results: We identified the benefits (e.g., maintain software development flow, improve developers' mental model, and foster entrepreneurship) and disadvantages (e.g., negative impact on developers' personality and damage to developers' reputation) of using LLMs at individual, team, organisation, and society levels; as well as best practices on how to adopt LLMs. Conclusion: Critically, we present the trade-offs that software practitioners, teams, and organisations face in working with LLMs. Our findings are particularly useful for software team leaders and IT managers to assess the viability of LLMs within their specific context.

Automated feedback generation plays a crucial role in enhancing personalized learning experiences in computer science education. Among different types of feedback, next-step hint feedback is particularly important, as it provides students with actionable steps to progress towards solving programming tasks. This study investigates how students interact with an AI-driven next-step hint system in an in-IDE learning environment. We gathered and analyzed a dataset from 34 students solving Kotlin tasks, containing detailed hint interaction logs. We applied process mining techniques and identified 16 common interaction scenarios. Semi-structured interviews with 6 students revealed strategies for managing unhelpful hints, such as adapting partial hints or modifying code to generate variations of the same hint. These findings, combined with our publicly available dataset, offer valuable opportunities for future research and provide key insights into student behavior, helping improve hint design for enhanced learning support.

Retrieval-Augmented Generation (RAG) is widely used to mitigate hallucinations of Large Language Models (LLMs) by leveraging external knowledge. While effective for simple queries, traditional RAG systems struggle with large-scale, unstructured corpora where information is fragmented. Recent advances incorporate knowledge graphs to capture relational structures, enabling more comprehensive retrieval for complex, multi-hop reasoning tasks. However, existing graph-based RAG (GraphRAG) methods rely on unstable and costly relation extraction for graph construction, often producing noisy graphs with incorrect or inconsistent relations that degrade retrieval quality. In this paper, we revisit the pipeline of existing GraphRAG systems and propose LinearRAG (Linear Graph-based Retrieval-Augmented Generation), an efficient framework that enables reliable graph construction and precise passage retrieval. Specifically, LinearRAG constructs a relation-free hierarchical graph, termed Tri-Graph, using only lightweight entity extraction and semantic linking, avoiding unstable relation modeling. This new paradigm of graph construction scales linearly with corpus size and incurs no extra token consumption, providing an economical and reliable indexing of the original passages. For retrieval, LinearRAG adopts a two-stage strategy: (i) relevant entity activation via local semantic bridging, followed by (ii) passage retrieval through global importance aggregation. Extensive experiments on four datasets demonstrate that LinearRAG significantly outperforms baseline models. Our code and datasets are available at https://github.com/DEEP-PolyU/LinearRAG.

We conducted three 90 - minute workshops at Talenthub Op Zuid, each with a different group of participants (total N=24, MAge =17.6, SD=1.2, see S upplement for additional details). In the first workshop, participants reviewed the prior 13 personas from Stage 1 and critiqued them for gaps in relevance. The scoping personas generated from survey and forum data gave youth stakeholders a concrete starting point for consulting as experts by experience in initial co - design activities. They challenged the realism of the scoping personas . Using fill - in - the - blank templates to guide but not restrict their persona creation (created by a youth member of the research team with design training, see Supplement), youth added contextual details to the project personas, such as daily routines, stressors, and digital habits, and brainstormed plausible backstories involving bullying, school difficulties, or parental conflict. The second workshop engaged a new participant group who expanded on previous outputs and addressed additional questions on living environment and emotional support needs, as this was suggested as relevant by youth from the prior workshop . Participants revised or created new personas b ased on their own or peers' experiences. In t he third workshop, a new group of participants again reviewed prior co - creation and outputs and further refined the personas .

At seventy-three, the former front man of Talking Heads is still asking questions about what it means to be alive. "When you step onstage, it's a very artificial situation," Byrne said. "To pretend it's not--that isn't being authentic." If you spend enough time wandering around downtown Manhattan, the odds are that you'll eventually encounter the musician David Byrne riding a bicycle. One day this past June, pedalling alongside Byrne from his apartment in Chelsea to the Governors Island ferry, I watched at least a dozen New Yorkers clock his profile, whipping around to squint, softly pinching the arm of their companion and whispering, "Was that . . . By then, Byrne was gone, a tuft of white hair whizzing toward the horizon. Spotting Byrne on two wheels has become a New York City rite of passage, like sussing out the best halal cart in midtown, or dropping something important onto the subway tracks. During the few months that Byrne and I spent together, I never saw him traverse the ...

Palantir's CEO is good with ICE and says he defends human rights. But will Israel and Trump ever go too far for him? Alex Karp and I would not seem to have much in common. I work for WIRED, which does tough reporting on Trumpworld; Karp is the CEO of Palantir, a $450 billion firm that has contracts with agencies like the CIA and ICE and worked for the Israeli military during its campaign in Gaza. I live in the East Village of New York City, and the home Karp spends the most time in is a 500-acre compound in rural New Hampshire. I was a plain old English major, and he's got a law degree and a PhD in philosophy, studying under the legendary Jürgen Habermas. I consider myself a progressive; Karp regards that stuff as "pagan religion." But we can bond over one shared status: Both of us are alumni of Central High School, a Philadelphia magnet school. I have some years on the 58-year-old executive.)

Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better leverage narrow training data, we propose contrastive weight steering, a simple post-training method that edits the model parameters using weight arithmetic. We isolate a behavior direction in weight-space by subtracting the weight deltas from two small fine-tunes -- one that induces the desired behavior and another that induces its opposite -- and then add or remove this direction to modify the model's weights. We apply this technique to mitigate sycophancy and induce misalignment, and find that weight steering often generalizes further than activation steering, achieving stronger out-of-distribution behavioral control before degrading general capabilities. We also show that, in the context of task-specific fine-tuning, weight steering can partially mitigate undesired behavioral drift: it can reduce sycophancy and under-refusals introduced during fine-tuning while preserving task performance gains. Finally, we provide preliminary evidence that emergent misalignment can be detected by measuring the similarity between fine-tuning updates and an "evil" weight direction, suggesting that it may be possible to monitor the evolution of weights during training and detect rare misaligned behaviors that never manifest during training or evaluations.