Entity · model
Llama3-8B-Instruct
modelactive
llama3-8b-instruct-4fe1960c·6 events·first seen Aliases: Llama3-8B-Instruct, Llama-3-8B-Instruct, Llama-3.1-8B-Instruct
Co-occurring entities
Qwen3-4BDirect Preference Optimization (DPO)AlpacaEval 2Qwen2.5-7B-Instruct-1MSame Evidence, Different Target: Decoding How Diagnostic Evidence Bears on Causal Questions from Language-Model StatesQwen3-4B-Thinking-2507Self-Guided Test-Time TrainingLongBench-ProLongBench v2BGEMQuAKEWhen to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge EditingzsRECounterFactInstructional Segment EmbeddingsTraining LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference OptimizationGravity-Weighted Direct Preference OptimizationWildBenchMT-BenchGeneral Preference Reinforcement Learning
More like this (12)
Recent events (6)
Linear readouts of LLM hidden states decode causal reasoning about diagnostic evidence
Researchers introduce a paired-prompt benchmark testing whether language models can correctly match diagnostic evidence to causal claims that vary by population, estimand, or identifying assumptions — a task where surface-level cues can mislead. Using linear probes on final-token hidden states from Qwen2.5-7B, Qwen3-8B, and Llama-3.1-8B, they find balanced accuracy of 0.654–0.659 on a 49-pair benchmark spanning nine diagnostic families, exceeding permutation nulls and text-only baselines. The key finding is that hidden states contain linearly decodable information about causal relevance that is not fully captured by output logits or surface features.
Self-Guided Test-Time Training improves long-context LLM utilization by up to 15%
Researchers propose Self-Guided Test-Time Training (S-TTT), a method that addresses the degradation in accuracy LLMs exhibit on long inputs by having the model first identify relevant evidence spans before applying test-time training only to those spans. A preliminary study on LongBench-v2 shows that TTT on randomly sampled spans hurts performance while TTT on oracle spans substantially helps, motivating the self-guided selection approach. Evaluated on LongBench-v2 and LongBench-Pro with Qwen3-4B-Thinking-2507 and Llama-3.1-8B-Instruct, S-TTT achieves up to 15% relative accuracy improvement. The method offers a practical path to better long-context utilization without the prohibitive cost of full-context adaptation.
Dual-adapter routing system improves knowledge editing precision in LLMs
A new arXiv paper introduces a route-specialized dual-adapter architecture for knowledge editing in LLMs, separating the concerns of writing edits (edit adapter) and suppressing them when irrelevant (locality adapter). A relevance router gates which adapter is applied, addressing the locality problem in memory-assisted editing. Evaluated on CounterFact, zsRE, and MQuAKE benchmarks using Llama-3.1-8B-Instruct and Qwen3-8B, the method achieves best-in-class probability-preference accuracy across all three datasets. Ablations show the gain comes from the architectural separation rather than increased parameter capacity.
Gravity-Weighted DPO enforces multi-level instruction hierarchies in LLMs
Researchers introduce Gravity-Weighted DPO (GW-DPO), a preference-optimization objective that scales per-sample loss offsets by the structural distance between conflicting instruction levels, addressing the problem of uniform architectural privilege across trust levels in production LLMs. The work formalizes a 5-level instruction hierarchy with ten pairwise priority relations and combines GW-DPO with hierarchy-specific delimiter tokens and Instructional Segment Embeddings (ISE). Evaluated on Llama-3.1-8B-Instruct, the bilateral GW-DPO schedule Pareto-improves over standard DPO on macro pairwise priority adherence while cutting over-refusal rates in half. The approach directly targets prompt injection vulnerabilities arising from models' inability to resolve competing instructions by privilege level.
General Preference Reinforcement Learning (GPRL): Bridging Online RL and Preference Optimization for Open-Ended Tasks
GPRL proposes a new alignment framework that replaces scalar reward models with a General Preference Model (GPM) embedding responses into k skew-symmetric subspaces to capture multi-dimensional, intransitivity-aware preferences. The method computes per-dimension group-relative advantages, normalizes across axes, and uses a closed-loop drift monitor to detect and correct single-axis reward hacking during training. Starting from Llama-3-8B-Instruct, GPRL achieves a 56.51% length-controlled win rate on AlpacaEval 2.0 and outperforms SimPO and SPPO on Arena-Hard, MT-Bench, and WildBench. The work directly addresses the gap between verifiable-reward online RL (strong on math/code) and preference optimization (strong on open-ended tasks).
Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)
Researchers from BAIR propose two fine-tuning-based defenses against prompt injection attacks: StruQ (Structured Instruction Tuning) and SecAlign (Special Preference Optimization). Both methods use a Secure Front-End with special delimiter tokens to separate trusted prompts from untrusted data, then fine-tune LLMs to ignore injected instructions. SecAlign, which uses DPO-style preference optimization, reduces attack success rates to under 15% against strong optimization-based attacks—more than 4x better than prior SOTA—while preserving model utility on AlpacaEval2.