Almanac
model

Llama3-8B-Instruct

modelactivellama3-8b-instruct-4fe1960c·4 events·first seen 1mo ago

Aliases: Llama3-8B-Instruct, Llama-3-8B-Instruct, Llama-3.1-8B-Instruct

Co-occurring entities

More like this (12)

Recent events (4)

7arXiv · cs.CL·28d ago·source ↗

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).

6arXiv · cs.CL·7d ago·source ↗

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.

4arXiv · cs.LG·2d ago·source ↗

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.

6Berkeley Ai Research (Bair) Blog·1mo ago·source ↗

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.