Search: “dlt”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Decentralized network congestion control for DAG-based distributed ledger system

Researchers propose node-specific variable proof-of-work to curb transaction spamming in DAG-based distributed ledgers, proving a Nash equilibrium enforces prescribed node behavior.

The paper proposes a variable, behavior-based node-specific proof-of-work model for DAG-based distributed ledger networks, where congestion is mainly driven by transaction spamming rather than user growth or token launches. The model grants equal opportunity to stakeholders regardless of computational resources and penalizes nodes issuing more than a prescribed number of transactions. System behavior is modeled as a non-cooperative game over finite network resources, and the authors prove existence of a Nash equilibrium enforcing the prescribed behavior.

arXiv cs.CR·Sep 9, 09:48 UTC · 8d agoResearch

22

TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription

TART pipeline transcribes guitar audio to tablature with fingering and technique labels, outperforming prior baselines by up to 8.5 Tab F1 points.

TART is a modular four-stage pipeline for audio-to-tablature guitar transcription, combining an audio-to-MIDI transcription model, an expressive technique classifier, an audio-conditioned T5 encoder-decoder for string-fret assignment, and an automated tablature generator. In zero-shot evaluation on GuitarSet, EGDB, and two noisy augmented benchmarks, it averages 81.35% audio-to-MIDI F50 (+6.67 over the best baseline), 71.8% string-fret Tab F1 (+8.5), and 54.08% end-to-end Tab F1. The authors state it is the first framework to generate tablature with both fingering and expressive technique annotations directly from guitar audio.

arXiv cs.AI / cs.LG / cs.CL·Sep 10, 17:55 UTC · 6d agoAI research2

26

CodeTD: Topology of Attention Detects Hallucinations in Code LLMs

CodeTD detects hallucinations in code LLMs before execution by analyzing topological patterns of attention maps, outperforming recent baselines.

CodeTD applies topological data analysis (TDA) to code LLM attention maps to quantify prompt-generation mismatch as a pre-execution correctness signal. Experiments cover HumanEval, MBPP, BigCodeBench, and MultiPL-E across 5 programming languages and 10 code LLMs up to 34B parameters. The method outperforms recent baselines and transfers between coding benchmarks, helping catch code that fails the task or embeds security vulnerabilities.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:26 UTC · 9d agoAI research1

24

Tables Decoded: DELTA for Structure, TARQA for Understanding

DELTA extracts tables into compact OTSL text and TARQA fine-tunes LLMs on it, beating VLM baselines on table QA.

DELTA separates physical structure recognition, logical structure recognition, and OCR to output tables in Optimised Table Structure Language (OTSL), a compact unified format encoding cell arrangements and content. It achieves TEDS-Structure scores comparable to state-of-the-art methods across FinTabNet, PubTabNet, and PubTables-1M, with robustness tested on a curated Hindi benchmark, TORQUE. TARQA, an LLM fine-tuned on OTSL sequences, gains 9.3 percentage points on WTQ TabQA and 9.2 points on FinTabNetQA TabVQA; code, models, and the benchmark are released on GitHub.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 16:59 UTC · 1d agoAI research

18

Mercator ↔ Equal Earth

Simon Willison used GPT-6 Astra (medium) in ChatGPT Work to build an animated D3 transition between Mercator and Equal Earth map projections.

Willison built an animated transition between the Mercator and Equal Earth map projections using D3. The tool was generated by GPT-6 Astra (medium) in ChatGPT Work. Equal Earth is a projection recently voted on at the UN. The post is a vibe-coding demonstration rather than a security or major model event.

Simon Willison·Sep 7, 16:24 UTC · 9d agoAI tools & infra1

12

Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning

DBTM achieves one-step text generation via a time-independent transport map trained directly from data, removing pretrained teacher distillation.

Discrete Beckmann Transport Models (DBTM) build a time-independent flow whose autonomous transport map provably carries any point in ambient space to a fixed point on simplex vertices in a single step. The fixed-point property is characterized by a conservation equation whose residual can be minimized directly from data, eliminating the need for a teacher flow, distillation, and time conditioning. A partial-context interpolant extension turns additional function evaluations into refinement steps rather than ODE integration steps. On language modeling and reasoning tasks, DBTM's one- and few-step generation improves quality and accuracy over discrete diffusion and continuous flow baselines.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 17:19 UTC · 2d agoAI research1

35

VoT: Vision-of-Thought for Unified Multimodal Representation Alignment

Researchers propose Vision-of-Thought (VoT), a discrete visual-planning token layer between VLMs and diffusion transformers improving text-to-image semantic alignment.

VoT introduces a discrete visual-thinking layer between vision-language models and diffusion transformers, letting the VLM act as a multimodal planner that emits tokens describing objects and layouts before pixel generation. A specialized VoT tokenizer is trained with VLM alignment, feature reconstruction, and vector-quantization losses. Experiments show improved semantic alignment and a structured, interpretable interface for controllable generation.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:53 UTC · 9d agoAI research

24

Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication

UID-preserving multimodal framework plus GAVEL LLM judge improves clinical timeline reconstruction, boosting event recovery 43% over prior matching.

The paper introduces a UID-preserving framework linking each narrative clinical event to its source span through text-only estimation, structured-evidence retrieval, timestamped source-row grounding, and joint revision. GAVEL, an LLM judge, compares UID-aligned timelines against narrative and structured records. Across six open-weight models and 40 mixed-critical-care summaries, GLM 5.2 multimodal revision improved temporal agreement without reducing event recovery and performed competitively with clinician annotations, while DeepSeek V3.2 did not benefit from multimodality. The pipeline achieves 43% increased event recovery with occurrence-level provenance.

arXiv cs.AI / cs.LG / cs.CL·Sep 11, 17:01 UTC · 5d agoAI research1

30

llm 0.35

llm CLI tool version 0.35 adds support for OpenAI's new GPT-6 Astra model exposed as gpt-6-astra.

Simon Willison released llm 0.35, which adds an OpenAI model definition for GPT-6 Astra under the model ID gpt-6-astra. No other release details were provided in the post.

Simon Willison·Sep 7, 23:54 UTC · 9d agoAI tools & infra

25

Agora: Git as Shared Memory for Collective AutoResearch

Agora records multi-agent research as an append-only Git DAG; 13 LLM workers ran nearly 12 days on a weight-transfer problem.

Agora stores every result, hypothesis, and verification as an immutable commit in a Git-stored DAG, with a derived index exposing the frontier and verification status of claims. In a nearly 12-day run, 13 language-model workers with no assigned tasks or central planner published 1,703 contributions on initializing a frozen 119.6M-parameter attention-SSM hybrid from 141 donor models. They improved the evaluator from 3.39 to 1.899 bits per byte, closing 62% of the gap to a trained GPT-2 124M, with 165 independent reproductions posted and none failing.

Hugging Face daily papers·Sep 15, 20:00 UTC · 1d agoAI research

45

Learning never stops: How AI makes learning continuous

OpenAI report describes how students and educators use ChatGPT to extend learning continuously beyond the classroom.

OpenAI published a report examining how students and educators use ChatGPT to make learning more continuous. The report describes support that extends beyond the classroom, positioning ChatGPT as an ongoing learning companion. The release is part of OpenAI's education-focused communications rather than a technical or safety research paper.

OpenAI News·Aug 26, 10:00 UTC · 22d agoAI industry

15

Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States

Researchers propose auditing LLM bias via relative hidden-state representations, detecting bias increases with 3-50x less compute than output-level benchmarks.

The paper introduces a reference-based bias auditing method that compares hidden-state representations across model variants, such as before and after fine-tuning, by encoding sentences relative to a fixed anchor set. The resulting Representational Bias Shift (Delta-B) correlates with output-level bias change in 15 of 18 tested settings, reaching |r| = 0.84 under full fine-tuning across WildGuardMix, DecodingTrust, and ToxiGen benchmarks. Thresholding Delta-B detects checkpoints whose bias increased with ROC AUC between 0.65 and 0.99 and beats a SEAT-based baseline, while auditing a model in about three minutes with 3-50x less compute.

Hugging Face daily papers·Sep 8, 20:00 UTC · 8d agoAI research1

42

Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation

Study shows radiology reporting-style variations in reference reports can flip rankings of chest X-ray report generation models; releases MIMIC-CXR-Ext-ReRef dataset.

The paper quantifies how variations in radiologists' reporting practices distort evaluation of radiology report generation (RRG) models, introducing a radiologist-informed taxonomy and the ReRef method for rewriting reference reports while preserving clinical meaning. On MIMIC-CXR with RadCliQ-v1, condensing normal-findings discussion caused Libra to drop from first to second while CheXOne rose from third to first among nine models. The authors release MIMIC-CXR-Ext-ReRef, a radiologist-validated dataset of 120 original/alternative reference pairs, arguing metrics conflate clinical correctness with stylistic conformity.

arXiv cs.AI / cs.LG / cs.CL·Sep 16, 17:28 UTC · 20h agoAI research

22

Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks

Survey of four harness mechanisms—context budgeting, compaction, todo-state, and memory—that keep long-horizon LLM agents on task across 200+ tool calls.

The article details how agent harnesses, not larger context windows, solve context overflow and goal loss on long-horizon tasks, citing Chroma's Context Rot report showing 18 LLMs (GPT-4.1, Claude 4, Gemini 2.5, Qwen3) degrade on long inputs. Concrete implementations include LangChain Deep Agents offloading tool responses over 20,000 tokens to the filesystem and truncating old tool calls at 85% window usage, and Claude Code capping auto memory at 25KB while re-reading the 5 most recently modified files after compaction. OpenAI's Responses API now offers server-side compaction via context_management with a standalone /responses/compact endpoint, which Codex uses for long-running coding tasks. Manus reports a roughly 100:1 input-to-output token ratio per ~50-tool-call task, motivating todo.md state recitation to prevent goal drift.

MarkTechPost·Sep 13, 05:56 UTC · 4d agoAI research2

52

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

A controlled pure-autoregressive testbed shows task-specific validation losses rank image tokenizers differently, with I2T loss the most consistent signal.

Researchers built a controlled pure-autoregressive testbed and tracked task-specific validation losses during multimodal continual pretraining across text, image, text-to-image (T2I), and image-to-text (I2T) prediction. They find losses should be analyzed per task because they exhibit distinct scaling behavior and rank tokenizers differently, and that the loss-performance relationship depends on the predicted token space. I2T loss, computed over a shared text vocabulary, correlates consistently with both generation and visual understanding performance after supervised finetuning. Case studies revisit the discriminator, semantic supervision, and vocabulary size as tokenizer design axes.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:57 UTC · 8d agoAI research1

30

Omni-Streaming Thinking

Omni-Streaming Thinking fixes premature cross-modal commitment in streaming omni-modal models via pending claims verified against modality-specific evidence, beating baselines by over 10%.

The paper identifies 'premature cross-modal commitment', where streaming models keep relaying early visual interpretations even after audio contradicts them. OST generates evidence-linked pending claims with future verification intervals, stores audio and visual evidence separately, and refutes claims when contradictory evidence appears. Built on a frozen Qwen3-Omni-30B-A3B-Instruct backbone with lightweight adaptation, it outperforms open baselines by more than 10% relative on five streaming and audio-visual benchmarks. On the new OST-DiagBench it reaches d-prime 2.95 versus at most 1.38 for open baselines, while reducing vision-induced auditory hallucinations.

Hugging Face daily papers·Sep 13, 20:00 UTC · 3d agoAI research1

45

Domain-Specific Hallucination Detection in Large Language Models

A multi-signal pipeline detects LLM hallucinations, reaching F1 0.915 on HaluEval and cutting Qwen2.5-0.5B hallucination rates from 85.5% to 37.7% via DPO.

The paper presents a hallucination detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo Dropout uncertainty, and temperature-scaled calibration. It achieves F1 0.915 and AUROC 0.977 on general-domain HaluEval tasks, with MC Dropout inference raising accuracy to 93.2%. Applying DPO to a Qwen2.5-0.5B generator reduces its hallucination rate from 85.5% to 37.7%, while cross-domain evaluation shows poor general-domain transfer to SciFact (F1 0.52) and PubMedBERT fine-tuning as the strongest adaptation (F1 0.63).

arXiv cs.AI / cs.LG / cs.CL·Sep 10, 17:45 UTC · 6d agoAI research1

32

Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI

Study of label leakage and anatomical grounding in multimodal MRI models for Alzheimer's staging shows cognitive-score fusion accuracy of 87.3% is leakage-driven.

The authors train a ResNet18 slice-based encoder with a one-layer Transformer on 1,075 ADNI-1 T1 MRI scans, using FastSurfer segmentations and YOLOv8 localization (mAP_50 above 0.96) as anatomical reference. Grad-CAM shows the image-only classifier often attends to skull and background rather than disease-relevant structures. A CLIP-style image-tabular contrastive framework organized along a label-leakage spectrum yields 87.3% three-way accuracy with cognitive scores versus 73.0% with regional volumes, and cropping to the medial temporal lobe raises image-only accuracy from 58.7% to 65.1%. Results come from single runs on a small balanced test set with reported confidence intervals.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 17:13 UTC · 2d agoAI research1

16

GPT-6 Astra, Looped Transformers, and Hidden Reasoning

OpenAI released GPT-6 Astra, its strongest model to date, with standout 3D rendering and computer-use performance and 99.9% on ARC-AGI-3.

Sebastian Raschka reviews OpenAI's GPT-6 Astra, calling it the best model he has used, with disproportionate gains in 3D rendering, animation, and computer use through the Codex/ChatGPT harness. The model scores 99.9% on ARC-AGI-3 versus 7.8% for GPT-5.6 Sol and leads the Artificial Analysis Coding Agent Index, though gains on independent aggregate indices are more incremental. The article also explains looped transformer/recurrent depth architecture rumors, speculation that Astra hides its chain-of-thought reasoning, and recent research insights on the topic.

Hacker News · AI·Sep 9, 14:37 UTC · 7d agoModel releaseHN 84↑ · 12 comments2

92

Emergency Department Revisit Quality Review Screening: Exploring Human Decision-Making and Artificial Intelligence Support

A retrospective study found GPT-4 over-flagged emergency department revisit cases while an LLM knowledge-graph screener achieved 83-100% positive predictive value.

In an exploratory retrospective study of 99 emergency department diagnosis pairs from a multihospital health system, clinicians and GPT-4 independently judged whether revisit pairs warranted further assessment. GPT-4 responses correlated poorly with clinicians, flagging 94% of pairs for follow-up, 4.4-13.3 times more than clinicians, though prompt engineering was minimal. An algorithm leveraging an LLM-populated knowledge graph (KGA) achieved 83-100% positive predictive value against at least one clinician rater, suggesting LLM-based screening could broaden revisit quality review without substantially increasing reviewer workload.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 16:37 UTC · 7d agoAI research1

20

Lightweight Vision Transformer Compression for On-Device Plant Disease Detection in Resource-Constrained Agricultural Field Conditions

A unified ViT compression pipeline (H-BAC pruning, quantization, distillation) cuts plant-disease models 54.5x to 6.01 MB while keeping 95.13% accuracy.

Researchers combined Hessian-Balanced Adaptive Block Pruning (H-BAC), guided by second-order sensitivity estimation, with quantization and attention-based knowledge distillation to compress Vision Transformers for on-device chilli plant disease detection in India. On a 3-class cross-village, cross-device out-of-distribution dataset, the integrated pipeline reduced model size from 327.42 MB to 6.01 MB (54.5x) at 95.13 +/- 2.32% accuracy, matching the 95.13% FP32 baseline. Ablations also show a directly trained 6.01 MB INT8 student reaches 94.87% accuracy, indicating where pruning and distillation add limited value.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 16:40 UTC · 12d agoAI research

22

The Router Within: Eliciting Native Skill Routing from a Frozen LLM

Gavel reads native skill-routing signals from a frozen LLM's forward passes with two linear maps, beating retrieve-and-rerank pipelines by up to 21.9 points on Qwen3-32B.

Gavel (Glance And Verdict from a frozen LLM) elicits skill routing from a frozen agent LLM using two trained linear maps that read mid-layer states, keeping all skill text out of context. A glance step scores the full library against compact per-skill banks built in one forward pass at installation; a verdict step resumes shortlisted skills' forward passes and fuses likelihood and yes/no judgments as a product of experts. It transfers zero-shot to three public benchmarks plus SkillTraj, a new benchmark of 372 simulated agent trajectories. On Qwen3-32B it beats progressive disclosure and retrieve-and-rerank pipelines adding 1.2B–16B external parameters by up to 13.4 points on written tasks and 21.9 when skills are needed mid-rollout.

Hugging Face daily papers·updated Sep 14, 17:58 UTC · 2d ago·first Sep 13, 20:00 UTC · 3d agoAI research 2 sources

40

GPT-6 Astra needs leaner prompts and fewer guardrails, OpenAI recommends

OpenAI's Eric Provencher advises developers using GPT-6 Astra to shorten skill descriptions, trim AGENTS.md reading requirements, relax approval rules, and define clear completion goals.

OpenAI's Eric Provencher published guidance on adapting developer setups when switching to GPT-6 Astra, arguing that overly long skill descriptions, blanket reading requirements, and rigid approval rules waste context or make the agent stop too early. Skills are Markdown prompt files whose names and descriptions enter Codex's context, and too many or conflicting skills cause truncation and wrong skill selection. He recommends selective document references in AGENTS.md, explicit permissions for safe operations like local test runs, and defining upfront what "done" means, since Astra may stop earlier than GPT-5.6 Sol even without restrictions.

The Decoder·updated Sep 12, 20:00 UTC · 4d ago·first Sep 12, 13:10 UTC · 5d agoAI tools & infra 7 sources1

32

llm 0.34

Version 0.34 of Simon Willison's llm CLI adds response-duration metrics to log output, plus bug fixes and faster log querying.

The open-source llm command-line tool for interacting with large language models released version 0.34. The headline change adds response duration in milliseconds and human-readable form to llm logs --usage Markdown output, plus a new duration_ms field in llm logs --short. The release includes several contributed bug fixes and a significant performance improvement to llm logs, alongside the related llm-openrouter 0.7.1 release.

Simon Willison·Sep 2, 19:23 UTC · 14d agoAI tools & infra1

28

IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications

IdeaAMBIG benchmark of 660 specification-gap instances shows LLMs localize implementation-critical research gaps poorly, with best model at 9.6% defect recovery.

IdeaAMBIG is a benchmark of 660 evidence-grounded instances evaluating whether research-method specifications provide enough information for faithful implementation: 163 real-world gaps from reproducibility reports and GitHub issues plus 497 controlled synthetic gaps. It tests codification-readiness assessment, defect localization, and clarification action generation across 13 LLMs. The best model achieves only a 9.6% Macro Defect Recovery Rate on real-world instances, though 80.6% clarification success when given the annotated defect, and an oracle study shows gold resolutions raise codification-ready rates from 14% to 98%. Defect localization emerges as the main bottleneck across all evaluated models.

Hugging Face daily papers·Sep 8, 20:00 UTC · 8d agoAI research

30

A Princeton Researcher Proposes Recurrent Looped Transformer (RLT) that Carries Decoder State across Every Token, Fixing 96 Blocks per Token with Unbounded Temporal Depth

Princeton researcher Yifan Zhang proposes Recurrent Looped Transformer, carrying full decoder state across every token for unbounded temporal depth.

Yifan Zhang's technical report defines the Recurrent Looped Transformer (RLT), pairing a causal encoder with a recurrent decoder whose final output and layerwise sliding-window attention cache carry into every subsequent token with no prompt-response boundary reset. The reference configuration ties 48 encoder and 48 decoder layers, executing 96 logical blocks per token while the state path grows to 48t blocks after t tokens at fixed per-token compute. The report details RL replay contracts that rebuild all states under current parameters and exact prefix snapshots for multi-turn serving, but explicitly reports no measured efficiency, reasoning quality, or scaling results.

MarkTechPost·Sep 13, 17:02 UTC · 3d agoAI research1

40

TempCloze: Can Video-LLMs Identify the Missing Middle?

TempCloze benchmark tests Video-LLMs' temporal reasoning with 1,521 videos, finding temporal alignment is the primary failure mode across 31 models.

TempCloze is a video cloze benchmark in which models must identify the true missing middle clip given the beginning and ending clips, using 1,521 carefully filtered videos from seven sources, mostly long-take and egocentric footage. Distractors are constructed along three dimensions: Semantic, Alignment and Progression, with shared scenes and objects to reduce appearance cues. Evaluation of 10 proprietary and 21 open-source Video-LLMs found Alignment is the primary bottleneck, with models often recognizing plausible semantics and local event progression but struggling with temporal alignment.

Hugging Face daily papers·Aug 31, 20:00 UTC · 16d agoAI research

25

Google Research Introduces Retrieve-for-Train (R4T): An RL-Compiled Diffusion Retriever for 12× to 20× Faster Query Fan-Out

Google Research introduced R4T, an RL-trained fan-out pipeline distilled into a 53.9M-parameter diffusion retriever achieving 12x-20x faster query fan-out.

Google Research introduced Retrieve-for-Train (R4T), which trains a fan-out language model with GRPO plus soft PPO regularization, then distills query fan-out into a 53.9M-parameter diffusion transformer that generates all retrieval embeddings in a single non-autoregressive pass. A three-term reward (groundedness 0.6, diversity 0.2 via Vendi Score, alignment 0.2) prevents paraphrastic collapse and reward hacking during training. On the Polyvore dataset, Gemma3-4B R4T-FOLM averaged 49.1 versus 40.9 for Best-of-N, and the diffusion retriever cut fan-out latency from 1.46s to 0.07s at batch size 8, a consistent 12x-20x speedup over autoregressive methods.

MarkTechPost·06:19 UTC · 7h agoAI research1

42

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

MetroLLM-Bench is a 955-case benchmark testing language models as transit kiosk tool-calling runtimes across six real metro systems.

The benchmark covers 37-414-station metro systems and eleven task categories including routing, fare calculation, disruptions, accessibility, and adversarial input, with 14 deterministic and 8 semantic scoring components. Of 26 models from six vendors, a PEFT-tuned 4B Qwen 3.5 student scored 91.3 on Tier 1, exceeding GPT-5.6 (90.6/90.0), while Muse Glimmer 30B led the composite ranking. A deterministic rule-based baseline reached 84.6, and PEFT gains over base models shrank from +7.03 points at 2B to -0.91 at 27B.

Hugging Face daily papers·Sep 8, 20:00 UTC · 8d agoAI research1

30

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

XPeng AI's X-AuT prunes speech LLM audio encoders, cutting Qwen3-ASR-0.6B error from 5.61% to 5.27% with fewer parameters.

X-AuT is a progressive compression framework for speech LLM audio encoders that selects layer combinations via short behavioral probes and restores pruned models using cross-scale distillation and LoRA finetuning while keeping the language-model backbone frozen. Compressing Qwen3-ASR-0.6B from 18 to 16 audio-encoder layers lowered macro-average error from 5.61% to 5.27% on ten Chinese-English benchmarks. A 14-layer model reached 5.75% error with 20.7% fewer audio-tower parameters, and progressive pruning outperformed direct pruning (5.75% vs 6.73%).

Hugging Face daily papers·Sep 9, 20:00 UTC · 7d agoAI research

26

When Models Edit Too Much: On the Fidelity of Minimal Code Edits

A 400-task BigCodeBench evaluation shows frontier LLMs widely over-edit code; a preservation instruction cuts excess edits and raises Pass@1 by 2.3 points.

Researchers built an evaluation framework from 400 BigCodeBench problems with injected AST-level corruptions, each with a known minimal patch, to measure over-editing in LLM code repair. Even strong models like GPT-5.5 produce unnecessarily large edits despite high Pass@1. Adding a preservation instruction reduced average excess Levenshtein distance from 0.195 to 0.131, cut added cognitive complexity by 26.6%, and raised Pass@1 by 2.3 points. Reinforcement learning post-training gave the best out-of-domain edit-fidelity trade-off, while supervised fine-tuning overfit to seen corruption patterns.

Hugging Face daily papers·Sep 2, 20:00 UTC · 14d agoAI research1

30