Searcharxiv⌕ Search

arXiv subjects

Xiaocong Yang

Publications and source records attributed to Xiaocong Yang.

15 recordsLinked to original sources

Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files

A coding agent works on repositories that can be far larger than its context window can hold. Prompt compressors and retrievers offer solutions to this problem, but patching an issue needs two things at once: the files that must change, and their code exactly as written, since the model must reproduce the lines it edits. Retrievers rank code by its similarity to the issue rather than by whether it must change, and compressors delete text to fit the budget. We show that at an equal token budget, an agent resolves more issues when the budget goes to choosing which files to show verbatim, as our simple selector CQ2-CARE does, than when it goes to pruning tokens or retrieving chunks. We fit every context to the same per-issue budget on 300 recent SWE-rebench issues and grade each patch with the benchmark's tests. With GPT-5.6 and Claude Opus 5, CQ2-CARE resolves 43.7% and 46.7% of the issues, 6.3 points more than the best of three compressors with either model, and 9.3 and 12.7 points more than the best of three retrievers. CQ2-CARE even resolves more issues than two methods trained for issue resolution, SweRank (by 0.7 and 1.7 points) and SWE-Pruner (by 2.0 and 7.3). Our analysis shows the defects of the baseline methods: retrievers often miss the files to edit, and compressors keep them but alter their text, so fewer patches apply. Exact-file selection needs no compression model and shows every line as the repository has it, so the model can quote the code it edits.

cs.SE↗

Resisting Harmful Instructions through Training-Free Weight Editing

Instruction-following language models can comply with requests that conflict with intended behaviors and safety alignment. We introduce a training-free weight-editing approach for reducing compliance with targeted undesirable instructions. Our method needs only forward passes on a small set of prompt pairs per target behavior, and because the edit is stored in the model's weights, changing or deleting instructions in the prompt cannot undo the weight modification. We evaluate the approach on two target harmful behaviors across five instruction-tuned models: instructed falsehood and instructed sexism. On two instructed-lying benchmarks, it improves mean honest response rates by 6.2 and 4.6 percentage points over the strongest alternative, significantly on three of the five models and within noise on the other two. In a controlled study of seven prompt formats, it maintains higher honest-response rates than single-layer activation steering when orders to lie arrive in single-turn formats not used to construct the edit. For instructed sexism, it reduces the mean sexist-response rate from 57.9% to 24.3%; combining the edit with a fairness prompt reduces it further to 11.9%. These results establish our contrast-based weight editing approach as an effective training-free intervention in two distinct behavioral domains, supporting its use both independently and alongside prompt-based safeguards.

cs.LG↗

DAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections

We propose DAGFormer, a Transformer language model whose cross-layer connections are planned by a jointly trained topology predictor. Beyond the residual connections in a standard Transformer, DAGFormer adds direct connections from earlier layers to later ones, and the predictor controls the strength of every connection based on input tokens. Unlike existing cross-layer routing architectures, which set each layer's connections separately, DAGFormer plans the routing of the whole model at once. On matched OLMo-2 pairs from 75M to 1B parameters, DAGFormer lowers WikiText-2 perplexity by 17% to 25% over the vanilla Transformer, and a 1B DAGFormer trained on 5B tokens outperforms the vanilla model trained on 10B. Against four routing baselines with the same data and budget, it reaches the lowest perplexity at 75M, 300M and 1B. The gain carries over to 13 commonsense, science, reading and math evaluation tasks (2.0 to 2.5 points higher mean accuracy at 300M and 1B) and to instruction finetuning (63% to 70% AlpacaEval win rate against the vanilla Transformer, leading every routing baseline), and under structured pruning DAGFormer degrades the least in five of six settings.

cs.CL↗

Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching

Large language models (LLMs) hold broad knowledge in one set of weights, but lack interpretability and trustworthy reasoning, especially in high-stakes use cases. A neuro-symbolic model, with its interpretable architecture and System 2 reasoning capacity, is a promising alternative if built at the scale of LLMs; however, its symbolic backbone is usually constructed with human effort, so existing neuro-symbolic models are bottlenecked by the scope of the symbol component and usually domain-specific. A data-driven method could instead build a larger symbolic system by aligning and merging existing ones. We target its first, foundational step: matching units across these heterogeneous systems. Our method, SAE-IDF, encodes a symbol in its native context into a sparse code with a sparse autoencoder (SAE), re-weights each dimension by its rarity and matches across systems. On 12 tasks across 6 kinds of symbolic system, SAE-IDF outperforms the same LLM's dense baseline on all tasks with Gemma-2-9B and all but one with Llama-3.1-8B, by up to 45 points, consistently across SAE layers and configurations. SAE-IDF is also interpretable: every dimension of the sparse code has a human-readable meaning, so each match decomposes into named concepts (features). Our work paves the way to a universal symbolic backbone.

cs.LG↗

Convex Optimization of Spiking Neural Networks with Global and Approximation Guarantees

Spiking neural networks (SNNs) have been proposed as energy-efficient alternatives to deep neural networks. Their training is non-convex and involves a non-differentiable spike function, so existing methods offer no guarantee of reaching a global optimum. We address this issue by formulating SNN optimization as an equivalent convex optimization problem. Specifically, we show that the weight-decay-regularized training problem for a class of threshold RNNs, including leaky integrate-and-fire SNNs, has zero duality gap and the same optimal value as a convex program. Since the resulting convex programs can have exponentially many variables in the amount of data, we introduce a practical randomized surrogate and establish a high-probability guarantee on its approximation quality. Empirically, the best convex variant outperforms surrogate-gradient training on addition and first-last-XOR, matches its performance on sequential MNIST, and trails a reservoir baseline on base-3 and base-5 addition.

cs.NE↗

Generative Interpretability via Scalable Neuro-Symbolic Models

As the use of Large Language Models moves from chatbots into agentic systems, where outputs become actions with irreversible consequences on reality, the existing paradigm on AI Interpretability research, post-hoc interpretability, is structurally inadequate for safe and trustworthy model deployment: it explains behavior after the fact but cannot audit or intervene in an inference computation before it commits to an output. We therefore argue for a shift toward \emph{generative interpretability}, an architectural property under which a model's inference pass natively exposes semantically meaningful checkpoints that are human-understandable and amenable to causal intervention. We show the merits of generative interpretability as comparison to other interpretability research paradigms, and propose Neuro-Symbolic Models as a concrete instantiation.

cs.LG↗

How Surface Viscoelasticity Eliminates Satellite Drops

Satellite drops form widely during the breakup of liquid threads and constitute deleterious byproducts across a broad range of industrial technologies, yet their complete suppression has remained a longstanding challenge. Here, we experimentally report that surface viscoelasticity introduced by a small amount of bovine serum albumin can fully eliminate satellite drops, via modulating the localized spatiotemporal topology near pinch-off singularity. During the late thinning stage, surface shear viscosity counterbalances the capillary and stably anchors the thinning neck at the midpoint between the two primary beads, fundamentally precluding satellite droplet formation. We further propose a scaling law to describe the unique self-similar thinning behaviors dictated by surface viscosity. These results shed light on the thinning dynamics of liquid threads with surface rheology and offer a promising strategy to eliminate satellite drops in practical applications.

physics.flu-dyn↗

Electric modification of mode competition in viscous films with insoluble surfactants on vertical fibers

This study investigates the coupled effects of an insoluble surfactant and a radial electric field on the stability of a viscous liquid film flowing down a vertical fiber. Starting from the governing equations in two dimensions, a reduced model in one dimension is derived using the long wave approximation to describe the coupled evolution of the interface and surfactant transport. Linear stability analysis identifies two distinct unstable modes: the Rayleigh-Plateau mode, which dominates at lower values of the Marangoni number $Ma$, and the Marangoni mode, which becomes dominant at higher values of $Ma$. The influence of the radial electric field is determined by the position of the outer electrode $β$. When $β<\mathrm{e}$, the electric field enhances both instabilities and narrows the stable interval in $Ma$ between the two modes. When $β>\mathrm{e}$, the electric field suppresses both modes and can completely eliminate the unstable region associated with the Marangoni mode even at a relatively small electric Weber number $E_b$. Continuation of the traveling wave solutions further shows that, when $β<\mathrm{e}$, the magnitude of the relative interfacial motion $I_{RP}$, generally increases with $E_b$. By contrast, the intensity of Marangoni convection $I_{M}$ varies only weakly at smaller values of $E_b$ and increases appreciably only when the electric field becomes sufficiently strong. Analysis of the stream function and the relative interfacial velocity reveals that the electric stress primarily intensifies the recirculation beneath the wave crest and reshapes the spatial distribution of the relative interfacial velocity.

physics.flu-dyn↗

LLM2IR: simple unsupervised contrastive learning makes long-context LLM great retriever

Modern dense information retrieval (IR) models usually rely on costly large-scale pretraining. In this paper, we introduce LLM2IR, an efficient unsupervised contrastive learning framework to convert any decoder-only large language model (LLM) to an information retrieval model. Despite its simplicity, the effectiveness is proven among different LLMs on multiple IR benchmarks including LoCo, LongEmbed and BEIR. We also find that models with a longer context length tend to have a stronger IR capacity by comparing task performances of models in the same model family. Our work not only provides an effective way to build IR models on the state-of-the-art LLMs, but also shed light on the relationship between information retrieval ability and model context length, which helps the design of better information retrievers.

cs.IR↗

Cascade Speculative Drafting for Even Faster LLM Inference

Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then reviews this draft to align with its output, and any acceptance by the target model results in a reduction of the number of the target model runs, ultimately improving efficiency. However, the drafting process in speculative decoding includes slow autoregressive generation and allocates equal time to generating tokens, irrespective of their importance. These inefficiencies collectively contribute to the suboptimal performance of speculative decoding. To further improve LLM inference, we introduce Cascade Speculative Drafting (CS Drafting), a speculative execution algorithm that incorporates two types of cascades. The Vertical Cascade eliminates autoregressive generation from neural models, while the Horizontal Cascade optimizes time allocation in drafting for improved efficiency. Combining both cascades, CS Drafting achieves greater speedup compared to the baselines in our experiments, while preserving the same output distribution as the target model.

cs.LG↗

Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval

Large language models (LLMs) are known to struggle with complicated reasoning tasks such as math word problems (MWPs). In this paper, we present how analogy from similarly structured questions can improve LLMs' problem-solving capabilities for MWPs. Specifically, we rely on the retrieval of problems with similar computational graphs to the given question to serve as exemplars in the prompt, providing the correct reasoning path for the generation model to refer to. Empirical results across six math word problem datasets demonstrate the effectiveness of our proposed method, which achieves a significant improvement of up to 6.7 percent on average in absolute value, compared to baseline methods. These results highlight our method's potential in addressing the reasoning challenges in current LLMs.

cs.CL↗

Parameter-Efficient Tuning with Special Token Adaptation

Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks. In this work, we introduce PASTA, in which we only modify the special token representations (e.g., [SEP] and [CLS] in BERT) before the self-attention module at each layer in Transformer-based models. PASTA achieves comparable performance to full finetuning in natural language understanding tasks including text classification and NER with up to only 0.029% of total parameters trained. Our work not only provides a simple yet effective way of parameter-efficient tuning, which has a wide range of practical applications when deploying finetuned models for multiple tasks, but also demonstrates the pivotal role of special tokens in pretrained language models

cs.CL↗

NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework

Pretrained language models have become the standard approach for many NLP tasks due to strong performance, but they are very expensive to train. We propose a simple and efficient learning framework, TLM, that does not rely on large-scale pretraining. Given some labeled task data and a large general corpus, TLM uses task data as queries to retrieve a tiny subset of the general corpus and jointly optimizes the task objective and the language modeling objective from scratch. On eight classification datasets in four domains, TLM achieves results better than or similar to pretrained language models (e.g., RoBERTa-Large) while reducing the training FLOPs by two orders of magnitude. With high accuracy and efficiency, we hope TLM will contribute to democratizing NLP and expediting its development.

cs.CL↗

Towards Natural Language Interfaces for Data Visualization: A Survey

Utilizing Visualization-oriented Natural Language Interfaces (V-NLI) as a complementary input modality to direct manipulation for visual analytics can provide an engaging user experience. It enables users to focus on their tasks rather than having to worry about how to operate visualization tools on the interface. In the past two decades, leveraging advanced natural language processing technologies, numerous V-NLI systems have been developed in academic research and commercial software, especially in recent years. In this article, we conduct a comprehensive review of the existing V-NLIs. In order to classify each paper, we develop categorical dimensions based on a classic information visualization pipeline with the extension of a V-NLI layer. The following seven stages are used: query interpretation, data transformation, visual mapping, view transformation, human interaction, dialogue management, and presentation. Finally, we also shed light on several promising directions for future work in the V-NLI community.

cs.HC↗

EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training

Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones. In this paper, we propose EVA, a Chinese dialogue system that contains the largest Chinese pre-trained dialogue model with 2.8B parameters. To build this model, we collect the largest Chinese dialogue dataset named WDC-Dialogue from various public social media. This dataset contains 1.4B context-response pairs and is used as the pre-training corpus of EVA. Extensive experiments on automatic and human evaluation show that EVA outperforms other Chinese pre-trained dialogue models especially in the multi-turn interaction of human-bot conversations.

cs.CL↗